Page 45

Subverting LLM Coders

Really interesting research: “An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection“:

Abstract: Large Language Models (LLMs) have transformed code completion tasks, providing context-based suggestions to boost developer productivity in software engineering. As users often fine-tune these models for specific applications, poisoning and backdoor attacks can covertly alter the model outputs. To address this critical security challenge, we introduce CODEBREAKER, a pioneering LLM-assisted backdoor attack framework on code completion models. Unlike recent attacks that embed malicious payloads in detectable or irrelevant sections of the code (e.g., comments), CODEBREAKER leverages LLMs (e.g., GPT-4) for sophisticated payload transformation (without affecting functionalities), ensuring that both the poisoned data for fine-tuning and generated code can evade strong vulnerability detection. CODEBREAKER stands out with its comprehensive coverage of vulnerabilities, making it the first to provide such an extensive set for evaluation. Our extensive experimental evaluations and user studies underline the strong attack performance of CODEBREAKER across various settings, validating its superiority over existing approaches. By integrating malicious payloads directly into the source code with minimal transformation, CODEBREAKER challenges current security measures, underscoring the critical need for more robust defenses for code completion.

Clever attack, and yet another illustration of why trusted AI is essential.

Tags: , , ,

Posted on November 7, 2024 at 7:07 AM • View Comments

IoT Devices in Password-Spraying Botnet

Microsoft is warning Azure cloud users that a Chinese controlled botnet is engaging in “highly evasive” password spraying. Not sure about the “highly evasive” part; the techniques seem basically what you get in a distributed password-guessing attack:

“Any threat actor using the CovertNetwork-1658 infrastructure could conduct password spraying campaigns at a larger scale and greatly increase the likelihood of successful credential compromise and initial access to multiple organizations in a short amount of time,” Microsoft officials wrote. “This scale, combined with quick operational turnover of compromised credentials between CovertNetwork-1658 and Chinese threat actors, allows for the potential of account compromises across multiple sectors and geographic regions.”

Some of the characteristics that make detection difficult are:

  • The use of compromised SOHO IP addresses
  • The use of a rotating set of IP addresses at any given time. The threat actors had thousands of available IP addresses at their disposal. The average uptime for a CovertNetwork-1658 node is approximately 90 days.
  • The low-volume password spray process; for example, monitoring for multiple failed sign-in attempts from one IP address or to one account will not detect this activity.

Tags: , , ,

Posted on November 6, 2024 at 7:02 AM • View Comments

AIs Discovering Vulnerabilities

I’ve been writing about the possibility of AIs automatically discovering code vulnerabilities since at least 2018. This is an ongoing area of research: AIs doing source code scanning, AIs finding zero-days in the wild, and everything in between. The AIs aren’t very good at it yet, but they’re getting better.

Here’s some anecdotal data from this summer:

Since July 2024, ZeroPath is taking a novel approach combining deep program analysis with adversarial AI agents for validation. Our methodology has uncovered numerous critical vulnerabilities in production systems, including several that traditional Static Application Security Testing (SAST) tools were ill-equipped to find. This post provides a technical deep-dive into our research methodology and a living summary of the bugs found in popular open-source tools.

Expect lots of developments in this area over the next few years.

This is what I said in a recent interview:

Let’s stick with software. Imagine that we have an AI that finds software vulnerabilities. Yes, the attackers can use those AIs to break into systems. But the defenders can use the same AIs to find software vulnerabilities and then patch them. This capability, once it exists, will probably be built into the standard suite of software development tools. We can imagine a future where all the easily findable vulnerabilities (not all the vulnerabilities; there are lots of theoretical results about that) are removed in software before shipping.

When that day comes, all legacy code would be vulnerable. But all new code would be secure. And, eventually, those software vulnerabilities will be a thing of the past. In my head, some future programmer shakes their head and says, “Remember the early decades of this century when software was full of vulnerabilities? That’s before the AIs found them all. Wow, that was a crazy time.” We’re not there yet. We’re not even remotely there yet. But it’s a reasonable extrapolation.

EDITED TO ADD: And Google’s LLM just discovered an exploitable zero-day.

Tags: , ,

Posted on November 5, 2024 at 7:08 AM • View Comments

Roger Grimes on Prioritizing Cybersecurity Advice

This is a good point:

Part of the problem is that we are constantly handed lists…list of required controls…list of things we are being asked to fix or improve…lists of new projects…lists of threats, and so on, that are not ranked for risks. For example, we are often given a cybersecurity guideline (e.g., PCI-DSS, HIPAA, SOX, NIST, etc.) with hundreds of recommendations. They are all great recommendations, which if followed, will reduce risk in your environment.

What they do not tell you is which of the recommended things will have the most impact on best reducing risk in your environment. They do not tell you that one, two or three of these things…among the hundreds that have been given to you, will reduce more risk than all the others.

[…]

The solution?

Here is one big one: Do not use or rely on un-risk-ranked lists. Require any list of controls, threats, defenses, solutions to be risk-ranked according to how much actual risk they will reduce in the current environment if implemented.

[…]

This specific CISA document has at least 21 main recommendations, many of which lead to two or more other more specific recommendations. Overall, it has several dozen recommendations, each of which individually will likely take weeks to months to fulfill in any environment if not already accomplished. Any person following this document is…rightly…going to be expected to evaluate and implement all those recommendations. And doing so will absolutely reduce risk.

The catch is: There are two recommendations that WILL DO MORE THAN ALL THE REST ADDED TOGETHER TO REDUCE CYBERSECURITY RISK most efficiently: patching and using multifactor authentication (MFA). Patching is listed third. MFA is listed eighth. And there is nothing to indicate their ability to significantly reduce cybersecurity risk as compared to the other recommendations. Two of these things are not like the other, but how is anyone reading the document supposed to know that patching and using MFA really matter more than all the rest?

Tags: , ,

Posted on October 31, 2024 at 11:43 AM • View Comments

Tracking World Leaders Using Strava

Way back in 2018, people noticed that you could find secret military bases using data published by the Strava fitness app. Soldiers and other military personal were using them to track their runs, and you could look at the public data and find places where there should be no people running.

Six years later, the problem remains. Le Monde has reported that the same Strava data can be used to track the movements of world leaders. They don’t wear the tracking device, but many of their bodyguards do.

Tags: ,

Posted on October 31, 2024 at 11:16 AM • View Comments

Simson Garfinkel on Spooky Cryptographic Action at a Distance

Excellent read. One example:

Consider the case of basic public key cryptography, in which a person’s public and private key are created together in a single operation. These two keys are entangled, not with quantum physics, but with math.

When I create a virtual machine server in the Amazon cloud, I am prompted for an RSA public key that will be used to control access to the machine. Typically, I create the public and private keypair on my laptop and upload the public key to Amazon, which bakes my public key into the server’s administrator account. My laptop and that remove server are thus entangled, in that the only way to log into the server is using the key on my laptop. And because that administrator account can do anything to that server­—read the sensitivity data, hack the web server to install malware on people who visit its web pages, or anything else I might care to do­—the private key on my laptop represents a security risk for that server.

Here’s why it’s impossible to evaluate a server and know if it is secure: as long that private key exists on my laptop, that server has a vulnerability. But if I delete that private key, the vulnerability goes away. By deleting the data, I have removed a security risk from the server and its security has increased. This is true entanglement! And it is spooky: not a single bit has changed on the server, yet it is more secure.

Read it all.

Tags: ,

Posted on October 30, 2024 at 10:48 AM • View Comments

Criminals Are Blowing up ATMs in Germany

It’s low tech, but effective.

Why Germany? It has more ATMs than other European countries, and—if I read the article right—they have more money in them.

EDITED TO ADD (11/14): Blog readers commented that countries like the Netherlands have laws requiring ATMs to have better security features. One that I thought particularly clever is a small “glue explosion” inside the safe that’s triggered when the ATM safe is breached. The glue renders the currency worthless.

Tags: , , ,

Posted on October 28, 2024 at 12:12 PM • View Comments

← Earlier EntriesLater Entries →

Sidebar photo of Bruce Schneier by Joe MacInnis.