Category
1,407 papers
Tool-using language agents can delegate and revoke permissions while acting through external services. We show that two authorization histories can have identical current permissions and identical all-pairs reachability yet require opposite decisions after the same direct-edge revocation. We formalize the information n...
The AI-safety version of the threat-model coverage gap is called the AI-safety version the threat-model coverage gap, and it is found that it persists in a current open-weight model, where harms surface in non-English prompts that English benchmarks miss.
JPPO is introduced, the first compound adversarial framework elevating the visible prompt to a first-class adversarial variable alongside image perturbations alongside image perturbations, motivating cost-aware robustness evaluation as a first-class security requirement for multimodal deployments.
Experimental results show that dual-embedding watermarking can offer state-of-the-art robustness, particularly against translation, while incurring relatively low computational overhead compared with other semantic schemes.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Neutral Prompting Attack (NPA), a highly stealthy attack paradigm in which semantically benign instructions, such as encouraging imagination and exhaustiveness, increase package hallucination propensity without containing explicit malicious intent is introduced.
Initial findings in two key areas of offensive security: Privacy-Preserving Machine Learning, and network traffic analysis are presented, by presenting initial findings in two key areas of offensive security.
This work characterize exactly when the observations contain enough independent information, give a matching optimal construction for unrestricted probes, and derive a more realistic estimator based on additions formed from the attacker's own data.
Challenger construction and evidence should be controlled, reported and interpreted explicitly when promotion is evaluated, and policy ordering changed with candidate comparability, no policy globally dominated, and earlier compatibility statements for a label-free estimator and a calibrated ensemble narrowed.
A systems-security case study of a two-node split-LLM training system whose privacy evaluation passed while leaving an observable channel untested, but the system is not thereby safe: five classes of attack, including those accumulating observations across training steps, were never measured.
FedIoC is contributed as a modular framework in which clients fold locally available structured threat indicators into their gradient updates, and is used to pinpoint the non-IID gradient structure as the main driver of recovery and to define the open problem of designing encoders that improve on it.
Binary reversing is fundamental to software understanding, vulnerability discovery, malware investigation, and firmware auditing. However, it remains inherently challenging due to the lossy transformation of semantic information during compilation. Recent advances in machine learning, large language models (LLMs), and...
The emergence of large language models (LLMs) has significantly accelerated recent research on LLM-based automatic grading (AG) systems. Benefiting from the strong instruction-following capabilities and broad prior knowledge of LLMs, educators can deploy AG systems across diverse tasks using only natural language rubri...
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.
