Page 30

NCSC Guidance on “Advanced Cryptography”

The UK’s National Cyber Security Centre just released its white paper on “Advanced Cryptography,” which it defines as “cryptographic techniques for processing encrypted data, providing enhanced functionality over and above that provided by traditional cryptography.” It includes things like homomorphic encryption, attribute-based encryption, zero-knowledge proofs, and secure multiparty computation.

It’s full of good advice. I especially appreciate this warning:

When deciding whether to use Advanced Cryptography, start with a clear articulation of the problem, and use that to guide the development of an appropriate solution. That is, you should not start with an Advanced Cryptography technique, and then attempt to fit the functionality it provides to the problem.

And:

In almost all cases, it is bad practice for users to design and/or implement their own cryptography; this applies to Advanced Cryptography even more than traditional cryptography because of the complexity of the algorithms. It also applies to writing your own application based on a cryptographic library that implements the Advanced Cryptography primitive operations, because subtle flaws in how they are used can lead to serious security weaknesses.

The conclusion:

Advanced Cryptography covers a range of techniques for protecting sensitive data at rest, in transit and in use. These techniques enable novel applications with different trust relationships between the parties, as compared to traditional cryptographic methods for encryption and authentication.

However, there are a number of factors to consider before deploying a solution based on Advanced Cryptography, including the relative immaturity of the techniques and their implementations, significant computational burdens and slow response times, and the risk of opening up additional cyber attack vectors.

There are initiatives underway to standardise some forms of Advanced Cryptography, and the efficiency of implementations is continually improving. While many data processing problems can be solved with traditional cryptography (which will usually lead to a simpler, lower-cost and more mature solution) for those that cannot, Advanced Cryptography techniques could in the future enable innovative ways of deriving benefit from large shared datasets, without compromising individuals’ privacy.

NCSC blog entry.

Posted on May 2, 2025 at 7:03 AMView Comments

WhatsApp Case Against NSO Group Progressing

Meta is suing NSO Group, basically claiming that the latter hacks WhatsApp and not just WhatsApp users. We have a procedural ruling:

Under the order, NSO Group is prohibited from presenting evidence about its customers’ identities, implying the targeted WhatsApp users are suspected or actual criminals, or alleging that WhatsApp had insufficient security protections.

[…]

In making her ruling, Northern District of California Judge Phyllis Hamilton said NSO Group undercut its arguments to use evidence about its customers with contradictory statements.

“Defendants cannot claim, on the one hand, that its intent is to help its clients fight terrorism and child exploitation, and on the other hand say that it has nothing to do with what its client does with the technology, other than advice and support,” she wrote. “Additionally, there is no evidence as to the specific kinds of crimes or security threats that its clients actually investigate and none with respect to the attacks at issue.”

I have written about the issues at play in this case.

Posted on April 30, 2025 at 7:12 AMView Comments

Applying Security Engineering to Prompt Injection Security

This seems like an important advance in LLM security against prompt injection:

Google DeepMind has unveiled CaMeL (CApabilities for MachinE Learning), a new approach to stopping prompt-injection attacks that abandons the failed strategy of having AI models police themselves. Instead, CaMeL treats language models as fundamentally untrusted components within a secure software framework, creating clear boundaries between user commands and potentially malicious content.

[…]

To understand CaMeL, you need to understand that prompt injections happen when AI systems can’t distinguish between legitimate user commands and malicious instructions hidden in content they’re processing.

[…]

While CaMeL does use multiple AI models (a privileged LLM and a quarantined LLM), what makes it innovative isn’t reducing the number of models but fundamentally changing the security architecture. Rather than expecting AI to detect attacks, CaMeL implements established security engineering principles like capability-based access control and data flow tracking to create boundaries that remain effective even if an AI component is compromised.

Research paper. Good analysis by Simon Willison.

I wrote about the problem of LLMs intermingling the data and control paths here.

Posted on April 29, 2025 at 7:03 AMView Comments

Windscribe Acquitted on Charges of Not Collecting Users’ Data

The company doesn’t keep logs, so couldn’t turn over data:

Windscribe, a globally used privacy-first VPN service, announced today that its founder, Yegor Sak, has been fully acquitted by a court in Athens, Greece, following a two-year legal battle in which Sak was personally charged in connection with an alleged internet offence by an unknown user of the service.

The case centred around a Windscribe-owned server in Finland that was allegedly used to breach a system in Greece. Greek authorities, in cooperation with INTERPOL, traced the IP address to Windscribe’s infrastructure and, unlike standard international procedures, proceeded to initiate criminal proceedings against Sak himself, rather than pursuing information through standard corporate channels.

Posted on April 28, 2025 at 2:17 PMView Comments

New Linux Rootkit

Interesting:

The company has released a working rootkit called “Curing” that uses io_uring, a feature built into the Linux kernel, to stealthily perform malicious activities without being caught by many of the detection solutions currently on the market.

At the heart of the issue is the heavy reliance on monitoring system calls, which has become the go-to method for many cybersecurity vendors. The problem? Attackers can completely sidestep these monitored calls by leaning on io_uring instead. This clever method could let bad actors quietly make network connections or tamper with files without triggering the usual alarms.

Here’s the code.

Note the self-serving nature of this announcement: ARMO, the company that released the research and code, has a product that it claims blocks this kind of attack.

Posted on April 24, 2025 at 3:35 PMView Comments

Regulating AI Behavior with a Hypervisor

Interesting research: “Guillotine: Hypervisors for Isolating Malicious AIs.”

Abstract:As AI models become more embedded in critical sectors like finance, healthcare, and the military, their inscrutable behavior poses ever-greater risks to society. To mitigate this risk, we propose Guillotine, a hypervisor architecture for sandboxing powerful AI models—models that, by accident or malice, can generate existential threats to humanity. Although Guillotine borrows some well-known virtualization techniques, Guillotine must also introduce fundamentally new isolation mechanisms to handle the unique threat model posed by existential-risk AIs. For example, a rogue AI may try to introspect upon hypervisor software or the underlying hardware substrate to enable later subversion of that control plane; thus, a Guillotine hypervisor requires careful co-design of the hypervisor software and the CPUs, RAM, NIC, and storage devices that support the hypervisor software, to thwart side channel leakage and more generally eliminate mechanisms for AI to exploit reflection-based vulnerabilities. Beyond such isolation at the software, network, and microarchitectural layers, a Guillotine hypervisor must also provide physical fail-safes more commonly associated with nuclear power plants, avionic platforms, and other types of mission critical systems. Physical fail-safes, e.g., involving electromechanical disconnection of network cables, or the flooding of a datacenter which holds a rogue AI, provide defense in depth if software, network, and microarchitectural isolation is compromised and a rogue AI must be temporarily shut down or permanently destroyed.

The basic idea is that many of the AI safety policies proposed by the AI community lack robust technical enforcement mechanisms. The worry is that, as models get smarter, they will be able to avoid those safety policies. The paper proposes a set technical enforcement mechanisms that could work against these malicious AIs.

Posted on April 23, 2025 at 12:02 PMView Comments

Sidebar photo of Bruce Schneier by Joe MacInnis.