Category
1,407 papers
It is shown that on a standard evaluation dataset, simple features beat most monitors without ever running the code, outranking 20 of 24 open-weight models prompted as monitors, suggesting that a high score on such a dataset is not by itself evidence of sabotage detection.
Large language model agents interact with online services through tool calls that may access private data or perform sensitive actions. Specialized providers can supply and maintain pre-execution safety auditing capabilities for agent operators. However, sending task descriptions, call arguments, and interaction histor...
ERASE, an on-policy self-distillation method that constructs its reference by erasing the injected region in place, is proposed, an on-policy self-distillation method that constructs its reference by erasing the injected region in place.
Web agents are increasingly deployed to complete tasks autonomously on real websites, where adversarially injected content can induce them to perform unauthorized actions. Existing evaluations primarily use fixed attacks or focus on a single attack type, and evaluate attacks at the text level rather than through real s...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Since large language model (LLM) agents rely on long-term memory, what they store now shapes what they do later. A memory manager decides how each input changes this memory and which records the agent acts on. It can fail in two ways: keeping a fact that has since changed (outdated memory), or storing a planted passage...
As Mixture-of-Experts (MoE) large language models are increasingly deployed in distributed environments, from federated learning to edge-cloud systems, their architecture harbors an underexplored landscape of security vulnerabilities. Moving beyond textual analysis, we uncover structural memorization: a novel vulnerabi...
Coding agents increasingly rely on automated approvers to decide whether a proposed shell command may run. Existing approvers, from rule-based checkers to guardrail models and deployed permission classifiers, base their decisions on the text of the request and command. Yet a command's behavior depends on the code it in...
Recursive self-improvement (RSI) enables large language models to advance their capabilities through successive updates, but these updates can also introduce new risks and weaken existing safeguards. In line with the AI-45{\deg} Law, we pursue Safety RSI, in which safety develops as an intrinsic capability alongside ge...
With the progressive capabilities of large language models (LLMs), researchers are finding ways to integrate them into the control loops of Open Radio Access Network (O-RAN) to enable slicing and resource management through user intents. However, integration of LLMs in the O-RAN control loop via the RAN Intelligent Con...
Evaluating approaches that improve the security of LLM code generation requires datasets that jointly assess security and functionality and remain adapted to the capabilities of the models being studied. However, existing benchmarks are costly to produce and are generally not calibrated to a chosen range of model capab...
LLM agents are increasingly used to automate vulnerability detection, but reliable detection is challenging because agents must distinguish subtle, security-relevant fixes from benign code variation. While underlying LLM capability has improved significantly, the accuracy of the agent still depends heavily on the harne...
LLM agents operating in untrusted workspaces face the risk of untrusted code execution during routine tasks, yet final reports and workspace states alone cannot reliably establish whether execution occurred. We introduce an evaluation framework that codes observation, reasoning, execution, and response behaviors from a...
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.
