Author Archives: Bruce Schneier

AI Industry is Trying to Subvert the Definition of “Open Source AI”

Posted on by

The Open Source Initiative has published (news article here) its definition of “open source AI,” and it’s terrible. It allows for secret training data and mechanisms. It allows for development to be done in secret. Since for a neural network, the training data is the source code—it’s how the model gets programmed—the definition makes no sense.

And it’s confusing; most “open source” AI models—like LLAMA—are open source in name only. But the OSI seems to have been co-opted by industry players that want both corporate secrecy and the “open source” label. (Here’s one …

Continue reading AI Industry is Trying to Subvert the Definition of “Open Source AI”→

Prompt Injection Defenses Against LLM Cyberattacks

Posted on by

Interesting research: “Hacking Back the AI-Hacker: Prompt Injection as a Defense Against LLM-driven Cyberattacks“:

Large language models (LLMs) are increasingly being harnessed to automate cyberattacks, making sophisticated exploits more accessible and scalable. In response, we propose a new defense strategy tailored to counter LLM-driven cyberattacks. We introduce Mantis, a defensive framework that exploits LLMs’ susceptibility to adversarial inputs to undermine malicious operations. Upon detecting an automated cyberattack, Mantis plants carefully crafted inputs into system responses, leading the attacker’s LLM to disrupt their own operations (passive defense) or even compromise the attacker’s machine (active defense). By deploying purposefully vulnerable decoy services to attract the attacker and using dynamic prompt injections for the attacker’s LLM, Mantis can autonomously hack back the attacker. In our experiments, Mantis consistently achieved over 95% effectiveness against automated LLM-driven attacks. To foster further research and collaboration, Mantis is available as an open-source tool: …

Continue reading Prompt Injection Defenses Against LLM Cyberattacks→

Subverting LLM Coders

Posted on by

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 com-
pletion 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…

Continue reading Subverting LLM Coders→

IoT Devices in Password-Spraying Botnet

Posted on by

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.”…

Continue reading IoT Devices in Password-Spraying Botnet→

AIs Discovering Vulnerabilities

Posted on by

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…

Continue reading AIs Discovering Vulnerabilities→

Roger Grimes on Prioritizing Cybersecurity Advice

Posted on by

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…

Continue reading Roger Grimes on Prioritizing Cybersecurity Advice→

Simson Garfinkel on Spooky Cryptographic Action at a Distance

Posted on by

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…

Continue reading Simson Garfinkel on Spooky Cryptographic Action at a Distance→