Entries Tagged "machine learning"

Page 2 of 5

Putting Undetectable Backdoors in Machine Learning Models

This is really interesting research from a few months ago:

Abstract: Given the computational cost and technical expertise required to train machine learning models, users may delegate the task of learning to a service provider. Delegation of learning has clear benefits, and at the same time raises serious concerns of trust. This work studies possible abuses of power by untrusted learners.We show how a malicious learner can plant an undetectable backdoor into a classifier. On the surface, such a backdoored classifier behaves normally, but in reality, the learner maintains a mechanism for changing the classification of any input, with only a slight perturbation. Importantly, without the appropriate “backdoor key,” the mechanism is hidden and cannot be detected by any computationally-bounded observer. We demonstrate two frameworks for planting undetectable backdoors, with incomparable guarantees.

First, we show how to plant a backdoor in any model, using digital signature schemes. The construction guarantees that given query access to the original model and the backdoored version, it is computationally infeasible to find even a single input where they differ. This property implies that the backdoored model has generalization error comparable with the original model. Moreover, even if the distinguisher can request backdoored inputs of its choice, they cannot backdoor a new input­a property we call non-replicability.

Second, we demonstrate how to insert undetectable backdoors in models trained using the Random Fourier Features (RFF) learning paradigm (Rahimi, Recht; NeurIPS 2007). In this construction, undetectability holds against powerful white-box distinguishers: given a complete description of the network and the training data, no efficient distinguisher can guess whether the model is “clean” or contains a backdoor. The backdooring algorithm executes the RFF algorithm faithfully on the given training data, tampering only with its random coins. We prove this strong guarantee under the hardness of the Continuous Learning With Errors problem (Bruna, Regev, Song, Tang; STOC 2021). We show a similar white-box undetectable backdoor for random ReLU networks based on the hardness of Sparse PCA (Berthet, Rigollet; COLT 2013).

Our construction of undetectable backdoors also sheds light on the related issue of robustness to adversarial examples. In particular, by constructing undetectable backdoor for an “adversarially-robust” learning algorithm, we can produce a classifier that is indistinguishable from a robust classifier, but where every input has an adversarial example! In this way, the existence of undetectable backdoors represent a significant theoretical roadblock to certifying adversarial robustness.

Turns out that securing ML systems is really hard.

Posted on February 24, 2023 at 7:34 AM • View Comments

Attacking Machine Learning Systems

The field of machine learning (ML) security—and corresponding adversarial ML—is rapidly advancing as researchers develop sophisticated techniques to perturb, disrupt, or steal the ML model or data. It’s a heady time; because we know so little about the security of these systems, there are many opportunities for new researchers to publish in this field. In many ways, this circumstance reminds me of the cryptanalysis field in the 1990. And there is a lesson in that similarity: the complex mathematical attacks make for good academic papers, but we mustn’t lose sight of the fact that insecure software will be the likely attack vector for most ML systems.

We are amazed by real-world demonstrations of adversarial attacks on ML systems, such as a 3D-printed object that looks like a turtle but is recognized (from any orientation) by the ML system as a gun. Or adding a few stickers that look like smudges to a stop sign so that it is recognized by a state-of-the-art system as a 45 mi/h speed limit sign. But what if, instead, somebody hacked into the system and just switched the labels for “gun” and “turtle” or swapped “stop” and “45 mi/h”? Systems can only match images with human-provided labels, so the software would never notice the switch. That is far easier and will remain a problem even if systems are developed that are robust to those adversarial attacks.

At their core, modern ML systems have complex mathematical models that use training data to become competent at a task. And while there are new risks inherent in the ML model, all of that complexity still runs in software. Training data are still stored in memory somewhere. And all of that is on a computer, on a network, and attached to the Internet. Like everything else, these systems will be hacked through vulnerabilities in those more conventional parts of the system.

This shouldn’t come as a surprise to anyone who has been working with Internet security. Cryptography has similar vulnerabilities. There is a robust field of cryptanalysis: the mathematics of code breaking. Over the last few decades, we in the academic world have developed a variety of cryptanalytic techniques. We have broken ciphers we previously thought secure. This research has, in turn, informed the design of cryptographic algorithms. The classified world of the NSA and its foreign counterparts have been doing the same thing for far longer. But aside from some special cases and unique circumstances, that’s not how encryption systems are exploited in practice. Outside of academic papers, cryptosystems are largely bypassed because everything around the cryptography is much less secure.

I wrote this in my book, Data and Goliath:

The problem is that encryption is just a bunch of math, and math has no agency. To turn that encryption math into something that can actually provide some security for you, it has to be written in computer code. And that code needs to run on a computer: one with hardware, an operating system, and other software. And that computer needs to be operated by a person and be on a network. All of those things will invariably introduce vulnerabilities that undermine the perfection of the mathematics…

This remains true even for pretty weak cryptography. It is much easier to find an exploitable software vulnerability than it is to find a cryptographic weakness. Even cryptographic algorithms that we in the academic community regard as “broken”—meaning there are attacks that are more efficient than brute force—are usable in the real world because the difficulty of breaking the mathematics repeatedly and at scale is much greater than the difficulty of breaking the computer system that the math is running on.

ML systems are similar. Systems that are vulnerable to model stealing through the careful construction of queries are more vulnerable to model stealing by hacking into the computers they’re stored in. Systems that are vulnerable to model inversion—this is where attackers recover the training data through carefully constructed queries—are much more vulnerable to attacks that take advantage of unpatched vulnerabilities.

But while security is only as strong as the weakest link, this doesn’t mean we can ignore either cryptography or ML security. Here, our experience with cryptography can serve as a guide. Cryptographic attacks have different characteristics than software and network attacks, something largely shared with ML attacks. Cryptographic attacks can be passive. That is, attackers who can recover the plaintext from nothing other than the ciphertext can eavesdrop on the communications channel, collect all of the encrypted traffic, and decrypt it on their own systems at their own pace, perhaps in a giant server farm in Utah. This is bulk surveillance and can easily operate on this massive scale.

On the other hand, computer hacking has to be conducted one target computer at a time. Sure, you can develop tools that can be used again and again. But you still need the time and expertise to deploy those tools against your targets, and you have to do so individually. This means that any attacker has to prioritize. So while the NSA has the expertise necessary to hack into everyone’s computer, it doesn’t have the budget to do so. Most of us are simply too low on its priorities list to ever get hacked. And that’s the real point of strong cryptography: it forces attackers like the NSA to prioritize.

This analogy only goes so far. ML is not anywhere near as mathematically sound as cryptography. Right now, it is a sloppy misunderstood mess: hack after hack, kludge after kludge, built on top of each other with some data dependency thrown in. Directly attacking an ML system with a model inversion attack or a perturbation attack isn’t as passive as eavesdropping on an encrypted communications channel, but it’s using the ML system as intended, albeit for unintended purposes. It’s much safer than actively hacking the network and the computer that the ML system is running on. And while it doesn’t scale as well as cryptanalytic attacks can—and there likely will be a far greater variety of ML systems than encryption algorithms—it has the potential to scale better than one-at-a-time computer hacking does. So here again, good ML security denies attackers all of those attack vectors.

We’re still in the early days of studying ML security, and we don’t yet know the contours of ML security techniques. There are really smart people working on this and making impressive progress, and it’ll be years before we fully understand it. Attacks come easy, and defensive techniques are regularly broken soon after they’re made public. It was the same with cryptography in the 1990s, but eventually the science settled down as people better understood the interplay between attack and defense. So while Google, Amazon, Microsoft, and Tesla have all faced adversarial ML attacks on their production systems in the last three years, that’s not going to be the norm going forward.

All of this also means that our security for ML systems depends largely on the same conventional computer security techniques we’ve been using for decades. This includes writing vulnerability-free software, designing user interfaces that help resist social engineering, and building computer networks that aren’t full of holes. It’s the same risk-mitigation techniques that we’ve been living with for decades. That we’re still mediocre at it is cause for concern, with regard to both ML systems and computing in general.

I love cryptography and cryptanalysis. I love the elegance of the mathematics and the thrill of discovering a flaw—or even of reading and understanding a flaw that someone else discovered—in the mathematics. It feels like security in its purest form. Similarly, I am starting to love adversarial ML and ML security, and its tricks and techniques, for the same reasons.

I am not advocating that we stop developing new adversarial ML attacks. It teaches us about the systems being attacked and how they actually work. They are, in a sense, mechanisms for algorithmic understandability. Building secure ML systems is important research and something we in the security community should continue to do.

There is no such thing as a pure ML system. Every ML system is a hybrid of ML software and traditional software. And while ML systems bring new risks that we haven’t previously encountered, we need to recognize that the majority of attacks against these systems aren’t going to target the ML part. Security is only as strong as the weakest link. As bad as ML security is right now, it will improve as the science improves. And from then on, as in cryptography, the weakest link will be in the software surrounding the ML system.

This essay originally appeared in the May 2020 issue of IEEE Computer. I forgot to reprint it here.

Posted on February 6, 2023 at 6:02 AM • View Comments

Threats of Machine-Generated Text

With the release of ChatGPT, I’ve read many random articles about this or that threat from the technology. This paper is a good survey of the field: what the threats are, how we might detect machine-generated text, directions for future research. It’s a solid grounding amongst all of the hype.

Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods

Abstract: Advances in natural language generation (NLG) have resulted in machine generated text that is increasingly difficult to distinguish from human authored text. Powerful open-source models are freely available, and user-friendly tools democratizing access to generative models are proliferating. The great potential of state-of-the-art NLG systems is tempered by the multitude of avenues for abuse. Detection of machine generated text is a key countermeasure for reducing abuse of NLG models, with significant technical challenges and numerous open problems. We provide a survey that includes both 1) an extensive analysis of threat models posed by contemporary NLG systems, and 2) the most complete review of machine generated text detection methods to date. This survey places machine generated text within its cybersecurity and social context, and provides strong guidance for future work addressing the most critical threat models, and ensuring detection systems themselves demonstrate trustworthiness through fairness, robustness, and accountability.

Posted on January 13, 2023 at 7:13 AM • View Comments

Adversarial ML Attack that Secretly Gives a Language Model a Point of View

Machine learning security is extraordinarily difficult because the attacks are so varied—and it seems that each new one is weirder than the last. Here’s the latest: a training-time attack that forces the model to exhibit a point of view: Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures.”

Abstract: We investigate a new threat to neural sequence-to-sequence (seq2seq) models: training-time attacks that cause models to “spin” their outputs so as to support an adversary-chosen sentiment or point of view—but only when the input contains adversary-chosen trigger words. For example, a spinned summarization model outputs positive summaries of any text that mentions the name of some individual or organization.

Model spinning introduces a “meta-backdoor” into a model. Whereas conventional backdoors cause models to produce incorrect outputs on inputs with the trigger, outputs of spinned models preserve context and maintain standard accuracy metrics, yet also satisfy a meta-task chosen by the adversary.

Model spinning enables propaganda-as-a-service, where propaganda is defined as biased speech. An adversary can create customized language models that produce desired spins for chosen triggers, then deploy these models to generate disinformation (a platform attack), or else inject them into ML training pipelines (a supply-chain attack), transferring malicious functionality to downstream models trained by victims.

To demonstrate the feasibility of model spinning, we develop a new backdooring technique. It stacks an adversarial meta-task onto a seq2seq model, backpropagates the desired meta-task output to points in the word-embedding space we call “pseudo-words,” and uses pseudo-words to shift the entire output distribution of the seq2seq model. We evaluate this attack on language generation, summarization, and translation models with different triggers and meta-tasks such as sentiment, toxicity, and entailment. Spinned models largely maintain their accuracy metrics (ROUGE and BLEU) while shifting their outputs to satisfy the adversary’s meta-task. We also show that, in the case of a supply-chain attack, the spin functionality transfers to downstream models.

This new attack dovetails with something I’ve been worried about for a while, something Latanya Sweeney has dubbed “persona bots.” This is what I wrote in my upcoming book (to be published in February):

One example of an extension of this technology is the “persona bot,” an AI posing as an individual on social media and other online groups. Persona bots have histories, personalities, and communication styles. They don’t constantly spew propaganda. They hang out in various interest groups: gardening, knitting, model railroading, whatever. They act as normal members of those communities, posting and commenting and discussing. Systems like GPT-3 will make it easy for those AIs to mine previous conversations and related Internet content and to appear knowledgeable. Then, once in a while, the AI might post something relevant to a political issue, maybe an article about a healthcare worker having an allergic reaction to the COVID-19 vaccine, with worried commentary. Or maybe it might offer its developer’s opinions about a recent election, or racial justice, or any other polarizing subject. One persona bot can’t move public opinion, but what if there were thousands of them? Millions?

These are chatbots on a very small scale. They would participate in small forums around the Internet: hobbyist groups, book groups, whatever. In general they would behave normally, participating in discussions like a person does. But occasionally they would say something partisan or political, depending on the desires of their owners. Because they’re all unique and only occasional, it would be hard for existing bot detection techniques to find them. And because they can be replicated by the millions across social media, they could have a greater effect. They would affect what we think, and—just as importantly—what we think others think. What we will see as robust political discussions would be persona bots arguing with other persona bots.

Attacks like these add another wrinkle to that sort of scenario.

Posted on October 21, 2022 at 6:53 AM • View Comments

Recovering Passwords by Measuring Residual Heat

Researchers have used thermal cameras and ML guessing techniques to recover passwords from measuring the residual heat left by fingers on keyboards. From the abstract:

We detail the implementation of ThermoSecure and make a dataset of 1,500 thermal images of keyboards with heat traces resulting from input publicly available. Our first study shows that ThermoSecure successfully attacks 6-symbol, 8-symbol, 12-symbol, and 16-symbol passwords with an average accuracy of 92%, 80%, 71%, and 55% respectively, and even higher accuracy when thermal images are taken within 30 seconds. We found that typing behavior significantly impacts vulnerability to thermal attacks, where hunt-and-peck typists are more vulnerable than fast typists (92% vs 83% thermal attack success if performed within 30 seconds). The second study showed that the keycaps material has a statistically significant effect on the effectiveness of thermal attacks: ABS keycaps retain the thermal trace of users presses for a longer period of time, making them more vulnerable to thermal attacks, with a 52% average attack accuracy compared to 14% for keyboards with PBT keycaps.

“ABS” is Acrylonitrile Butadiene Styrene, which some keys are made of. Others are made of Polybutylene Terephthalate (PBT). PBT keys are less vulnerable.

But, honestly, if someone can train a camera at your keyboard, you have bigger problems.

News article.

Posted on October 12, 2022 at 6:30 AM • View Comments

Inserting a Backdoor into a Machine-Learning System

Interesting research: “ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks, by Tim Clifford, Ilia Shumailov, Yiren Zhao, Ross Anderson, and Robert Mullins:

Abstract: Early backdoor attacks against machine learning set off an arms race in attack and defence development. Defences have since appeared demonstrating some ability to detect backdoors in models or even remove them. These defences work by inspecting the training data, the model, or the integrity of the training procedure. In this work, we show that backdoors can be added during compilation, circumventing any safeguards in the data preparation and model training stages. As an illustration, the attacker can insert weight-based backdoors during the hardware compilation step that will not be detected by any training or data-preparation process. Next, we demonstrate that some backdoors, such as ImpNet, can only be reliably detected at the stage where they are inserted and removing them anywhere else presents a significant challenge. We conclude that machine-learning model security requires assurance of provenance along the entire technical pipeline, including the data, model architecture, compiler, and hardware specification.

Ross Anderson explains the significance:

The trick is for the compiler to recognise what sort of model it’s compiling—whether it’s processing images or text, for example—and then devising trigger mechanisms for such models that are sufficiently covert and general. The takeaway message is that for a machine-learning model to be trustworthy, you need to assure the provenance of the whole chain: the model itself, the software tools used to compile it, the training data, the order in which the data are batched and presented—in short, everything.

Posted on October 11, 2022 at 7:18 AM • View Comments

Attacking the Performance of Machine Learning Systems

Interesting research: “Sponge Examples: Energy-Latency Attacks on Neural Networks“:

Abstract: The high energy costs of neural network training and inference led to the use of acceleration hardware such as GPUs and TPUs. While such devices enable us to train large-scale neural networks in datacenters and deploy them on edge devices, their designers’ focus so far is on average-case performance. In this work, we introduce a novel threat vector against neural networks whose energy consumption or decision latency are critical. We show how adversaries can exploit carefully-crafted sponge examples, which are inputs designed to maximise energy consumption and latency, to drive machine learning (ML) systems towards their worst-case performance. Sponge examples are, to our knowledge, the first denial-of-service attack against the ML components of such systems. We mount two variants of our sponge attack on a wide range of state-of-the-art neural network models, and find that language models are surprisingly vulnerable. Sponge examples frequently increase both latency and energy consumption of these models by a factor of 30×. Extensive experiments show that our new attack is effective across different hardware platforms (CPU, GPU and an ASIC simulator) on a wide range of different language tasks. On vision tasks, we show that sponge examples can be produced and a latency degradation observed, but the effect is less pronounced. To demonstrate the effectiveness of sponge examples in the real world, we mount an attack against Microsoft Azure’s translator and show an increase of response time from 1ms to 6s (6000×). We conclude by proposing a defense strategy: shifting the analysis of energy consumption in hardware from an average-case to a worst-case perspective.

Attackers were able to degrade the performance so much, and force the system to waste so many cycles, that some hardware would shut down due to overheating. Definitely a “novel threat vector.”

Posted on June 16, 2022 at 6:02 AM • View Comments

Manipulating Machine-Learning Systems through the Order of the Training Data

Yet another adversarial ML attack:

Most deep neural networks are trained by stochastic gradient descent. Now “stochastic” is a fancy Greek word for “random”; it means that the training data are fed into the model in random order.

So what happens if the bad guys can cause the order to be not random? You guessed it—all bets are off. Suppose for example a company or a country wanted to have a credit-scoring system that’s secretly sexist, but still be able to pretend that its training was actually fair. Well, they could assemble a set of financial data that was representative of the whole population, but start the model’s training on ten rich men and ten poor women drawn from that set ­ then let initialisation bias do the rest of the work.

Does this generalise? Indeed it does. Previously, people had assumed that in order to poison a model or introduce backdoors, you needed to add adversarial samples to the training data. Our latest paper shows that’s not necessary at all. If an adversary can manipulate the order in which batches of training data are presented to the model, they can undermine both its integrity (by poisoning it) and its availability (by causing training to be less effective, or take longer). This is quite general across models that use stochastic gradient descent.

Research paper.

Posted on May 25, 2022 at 10:30 AM • View Comments

Undetectable Backdoors in Machine-Learning Models

New paper: “Planting Undetectable Backdoors in Machine Learning Models“:

Abstract: Given the computational cost and technical expertise required to train machine learning models, users may delegate the task of learning to a service provider. We show how a malicious learner can plant an undetectable backdoor into a classifier. On the surface, such a backdoored classifier behaves normally, but in reality, the learner maintains a mechanism for changing the classification of any input, with only a slight perturbation. Importantly, without the appropriate “backdoor key”, the mechanism is hidden and cannot be detected by any computationally-bounded observer. We demonstrate two frameworks for planting undetectable backdoors, with incomparable guarantees.

First, we show how to plant a backdoor in any model, using digital signature schemes. The construction guarantees that given black-box access to the original model and the backdoored version, it is computationally infeasible to find even a single input where they differ. This property implies that the backdoored model has generalization error comparable with the original model. Second, we demonstrate how to insert undetectable backdoors in models trained using the Random Fourier Features (RFF) learning paradigm or in Random ReLU networks. In this construction, undetectability holds against powerful white-box distinguishers: given a complete description of the network and the training data, no efficient distinguisher can guess whether the model is “clean” or contains a backdoor.

Our construction of undetectable backdoors also sheds light on the related issue of robustness to adversarial examples. In particular, our construction can produce a classifier that is indistinguishable from an “adversarially robust” classifier, but where every input has an adversarial example! In summary, the existence of undetectable backdoors represent a significant theoretical roadblock to certifying adversarial robustness.

EDITED TO ADD (4/20): Cory Doctorow wrote about this as well.

Posted on April 19, 2022 at 3:12 PM • View Comments

Using Radar to Read Body Language

Yet another method of surveillance:

Radar can detect you moving closer to a computer and entering its personal space. This might mean the computer can then choose to perform certain actions, like booting up the screen without requiring you to press a button. This kind of interaction already exists in current Google Nest smart displays, though instead of radar, Google employs ultrasonic sound waves to measure a person’s distance from the device. When a Nest Hub notices you’re moving closer, it highlights current reminders, calendar events, or other important notifications.

Proximity alone isn’t enough. What if you just ended up walking past the machine and looking in a different direction? To solve this, Soli can capture greater subtleties in movements and gestures, such as body orientation, the pathway you might be taking, and the direction your head is facing—­aided by machine learning algorithms that further refine the data. All this rich radar information helps it better guess if you are indeed about to start an interaction with the device, and what the type of engagement might be.

[…]

The ATAP team chose to use radar because it’s one of the more privacy-friendly methods of gathering rich spatial data. (It also has really low latency, works in the dark, and external factors like sound or temperature don’t affect it.) Unlike a camera, radar doesn’t capture and store distinguishable images of your body, your face, or other means of identification. “It’s more like an advanced motion sensor,” Giusti says. Soli has a detectable range of around 9 feet­—less than most cameras­—but multiple gadgets in your home with the Soli sensor could effectively blanket your space and create an effective mesh network for tracking your whereabouts in a home.

“Privacy-friendly” is a relative term.

These technologies are coming. They’re going to be an essential part of the Internet of Things.

Posted on March 8, 2022 at 6:01 AM • View Comments

1 2 3 4 5

Sidebar photo of Bruce Schneier by Joe MacInnis.