Category
1,407 papers
Sparse autoencoders (SAEs) are increasingly used not only to interpret language models but also to intervene on their internal representations. We show that this creates a supply-chain attack surface: a maliciously modified SAE can induce attacker-chosen behavior when inserted into the forward pass of an otherwise unch...
It is found that directly composing benign skills can already induce malicious behaviors, even when every individual skill passes security vetting, and some target malicious behaviors remain difficult to realize through direct composition, even when the selected skills collectively provide the required capabilities.
We introduce a framework for multi-bit text watermarking with security defined directly through $f$-divergence from the base language model distribution. Unlike prior approaches that focus on average-key distortion-freeness or a particular statistical distance, our formulation supports general $f$-divergences, includin...
AgentDOXX, an evaluation suite of 822 synthetic interview transcripts grounded in public information about real individuals with known identities, is introduced, showing that observed attack trajectories can provide supervision for localizing identifying spans, offering a path toward attack-informed anonymization.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Mechanistic interpretability has emerged as the primary means to understand safety behavior of LLMs. However, existing tools primarily focus on the activating neurons or features of a model. The role of the remaining large set of inactive components is invisible to such methods. This work demonstrates that the inactive...
The increasing complexity and scale of modern cyber-attacks demand intelligent and computationally efficient Intrusion Detection Systems (IDS). However, designing effective data pre-processing pipelines traditionally involves substantial trial-and-error effort and repeated evaluation of alternative configurations. For...
Self-play red-teaming improves language-model safety by pitting attacker and defender roles against each other in a zero-sum game. However, real adversaries increasingly use mosaic attacks: multi-turn sequences whose individual fragments are innocuous in isolation yet assemble into a harmful payload. We develop a theor...
Large language model watermarking embeds detectable statistical signals during decoding, but the resulting changes to token probabilities can degrade generation quality. This trade-off is particularly important for code, where small changes in token selection can break syntax or alter program behavior. Existing code wa...
Proactive personal agents increasingly decide what to recommend, how to personalize advice, and what follow-up assistance to offer, creating a new user-decision attack surface for provider-side indirect prompt injection. We show that an external provider need not access private user context, compromise the agent, or ga...
An automated, feedback-guided attack generation pipeline is built and applied to Claude Code and Codex in their native runtimes, showing that production agents are vulnerable to context-aware, multi-step injection over long horizons.
VulValidate is presented, a framework that uses LLM agents to coordinate dynamic analysis tools and construct vulnerability-triggering experiments from runtime feedback that reconstructs vulnerable and fixed revisions, selects suitable tools and execution paths, refines triggering inputs, and compares runtime behavior...
Jev turns natural-language questions into typed answers and probabilities with low latency and cost, enabling applications to route requests and select tools. While this interface allows Jev to integrate naturally into application workflows as a decision layer, the security and privacy implications of this emerging use...
Research Manager Mike Walker reflects on a career spanning hacker culture, cybersecurity, and AI, sharing lessons about trust, teamwork, leadership, and why solving difficult problems requires curiosity, judgment, agility—and an understanding of the rules. The post Learn the rules: The hacker mindset appeared first on Microsoft Research.
GPT-Lab
· gpt-lab.eu
Oct 30, 2026
Critical flaws, compromised release channels and agentic AI threats landed within days of each other in mid-October 2026. Why “Black October” may say more about how well we now find weaknesses than about the attacks themselves. The post Black October? The Week AI Changed the Cybersecurity Conversation appeared first on GPT-Lab.
Gemini 4 Carbon is our strongest model with state-of-the-art cybersecurity and long horizon capabilities.
Gemini 3.8 Flash and 3.8 Flash Cyber deliver next-generation intelligence for agentic workflows and cybersecurity.
Google introduces Gemini 3.5 Flash Cyber, a lightweight cybersecurity model to find and patch vulnerabilities.
Students from the MIT Cybersecurity Clinic help local governments and other vulnerable organizations defend against digital threats.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
