// AI & Machine Learning
Intel Feed

In 2023 GitHub introduced CodeQL multi-repository variant analysis (MRVA). This functionality lets you run queries across thousands of projects using pre-built databases and drastically reduces the ti…

We’re getting Sigstore’s rekor-monitor ready for production use, making it easier for developers to detect tampering and unauthorized uses of their identities in the Rekor transparency log. This work,…

Memory safety bugs like use-after-free and buffer overflows remain among the most exploited vulnerability classes in production software. While AddressSanitizer (ASan) excels at catching these bugs du…

I recently attended the AI Engineer Code Summit in New York, an invite-only gathering of AI leaders and engineers. One theme emerged repeatedly in conversations with attendees building with AI: the be…

Go’s arithmetic operations on standard integer types are silent by default, meaning overflows “wrap around” without panicking. This behavior has hidden an entire class of security vulnerabilities from…

With browser-embedded AI agents, we’re essentially starting the security journey over again. We exploited a lack of isolation mechanisms in multiple agentic browsers to perform attacks ranging from th…

Software signatures carry an invisible expiration date. The container image or firmware you sign today might be deployed for 20 years, but the cryptographic signature protecting it may become untrustw…

Last year, our engineers submitted over 375 pull requests that were merged into non–Trail of Bits repositories, touching more than 90 projects from cryptography libraries to the Rust compiler. This wo…

Two popular AES libraries, aes-js and pyaes, “helpfully” provide a default IV in their AES-CTR API, leading to a large number of key/IV reuse bugs. These bugs potentially affect thousands of downstrea…

Before launching their Comet browser, Perplexity hired us to test the security of their AI-powered browsing features. Using adversarial testing guided by our TRAIL threat model, we demonstrated how fo…

If you’ve ever done Linux memory forensics, you know the frustration: without debug symbols that match the exact kernel version, you’re stuck. These symbols aren’t typically installed on production sy…

Account abstraction transforms fixed “private key can do anything” models into programmable systems that enable batching, recovery and spending limits, and flexible gas payment. But that programmabili…

Using dimensional analysis, you can categorically rule out a whole category of logic and arithmetic bugs that plague DeFi formulas. No code changes required, just better reasoning! One of the first le…

We’re releasing a new Claude plugin for developing and auditing code that implements dimensional analysis, a technique we explored in our most recent blog post . Most LLM-based security skills ask the…

This post is adapted from a talk I gave at [un]prompted , the AI security practitioner conference. Thanks to Gadi Evron for inviting me to speak. You can watch the recorded presentation below or downl…

Code coverage is one of the most dangerous quality metrics in software testing. Many developers fail to realize that code coverage lies by omission: it measures execution, not verification. Test suite…

Mixed Boolean-Arithmetic (MBA) obfuscation disguises simple operations like x + y behind tangles of arithmetic and bitwise operators. Malware authors and software protectors rely on it because no stan…

WhatsApp’s new “Private Inference” feature represents one of the most ambitious attempts to combine end-to-end encryption with AI-powered capabilities, such as message summarization. To make this poss…

We added a new chapter to our Testing Handbook: a comprehensive security checklist for C and C++ code . We’ve identified a broad range of common bug classes, known footguns, and API gotchas across C a…

Two weeks ago, Google’s Quantum AI group published a zero-knowledge proof of a quantum circuit so optimized, they concluded that first-generation quantum computers will break elliptic curve cryptograp…

Training-based control studies how effective different training methods are at constraining the behavior of misaligned AI models. A central example of a case where we want to control AI models is in d…

5 Cybersecurity Stocks Most Likely to Benefit as AI Threats Drive Budget Increases in 2026 24/7 Wall St.

Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model Big claims from Qwen about their latest open weight model: Qwen3.6-27B delivers flagship-level agentic coding performance, surpassing the previo…