Category
1,407 papers
A clear gap is identified between strong optimization performance and regulatory adherence in AI Act compliance, suggesting compliance is limited less by technology than by a focus on static performance over lifecycle safety, and underscoring an urgent need for security-by-design in safety-critical intelligent transpor...
Experiments demonstrate that DDPO significantly outperforms static prompt optimization methods, particularly on weakly aligned models and when handling semantically ambiguous benign prompts, successfully distinguishing them from genuinely harmful requests.
It is demonstrated that an attacker can embed a stealthy backdoor into an LLM-based robot controller by manipulating its instructions, triggered not by an external cue, but by a specific, rare sequence of the robot's own past actions.
Encoded-prompt attacks are evaluated almost entirely on their harmful arm: a benchmark sends obfuscated harmful requests and reports how often the model complied, and shows that on two of the four models the loss is caused by the protocol rather than by the character transformation, and on a third by the characters.
Reach audiences
Advertise in front of researchers, engineers, and readers.
It is shown that aligned vision-language models also condition refusal on a property of a request's form: whether an image is attached, holding everything the request asks fixed, which shifts benign refusal by tens of points.
StepTrigger, a contact-state-triggered backdoor attack for VLM-powered legged robots, is presented, a contact-state-triggered backdoor attack for VLM-powered legged robots that reveals a backdoor surface in proprioceptive and contact channels that is not captured by defenses focused only on language, vision, or action...
This work introduces Executable Semantic Commitments with Clean-Room Recovery (ESC-CR), a policy-backed framework for secure inter-agent code generation and recovery that preserves evidence-backed claims while suppressing unauthorized releases under matched computational budgets.
These results give the widely repeated qualitative recommendation of "balanced human-AI collaboration" a precise, testable form and suggest an interior-optimum capacity ratio as a concrete design target for security operations centers (SOCs), including those securing IT/OT-converged critical infrastructure.
AI-generated imagery evolves faster than benchmark-specific detector evaluations, making a single score an incomplete account of generalization. This paper evaluates Neural Defend ARCAS 1B across benchmark families without benchmark-specific parameter updates. We retain native aggregation and supplement it with record-...
It is shown that the compression method also affects privacy, and choosing the 4-bit method is therefore a deployment-time privacy decision, not only a question of speed and quality.
The selection-invariant communication compiler (SICC), which constrains this post-authorization representation kernel rather than prescribing templates, is introduced, which proves a compositional communication-layer guarantee.
This work introduces KEX-bench, a benchmark for evaluating coding agents on exploit primitive generation against real operating-system kernels, and evaluates state-of-the-art coding agents paired with frontier and open-weight models under fixed tool-call budgets.
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.
