AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
Category
1,407 papers
SSP-Bench reveals systematic failures of static evaluation, including near-zero correlation in safety rankings due to construct mixing, strong safety--over-refusal coupling, and hidden within-family regressions, and shows that static benchmarks can misrepresent model behavior, motivating dynamic, deployment-relevant ev...
Rigorous expert validation confirms seed plausibility and realism for meaningful LLM safety evaluation, and provides an expert-validated, finance-specific rubric that goes beyond disclaimer checks, aligns more closely with human experts than static one-size-fits-all rubrics, and reduces critical false negatives from 28...
Verifier reliability is not portable across tasks. A verifier-guided self-DPO pipeline with genuine held-out gains on MathVista (+9.6 points on self-training data, +8.0 held out) can be harmful on MMMU. The failure is invisible from the target-task self-training signal: over six learner-verifier configurations, MMMU se...
Adaptive Unlearning is presented, a post-deployment framework that surgically suppresses package hallucinations while preserving general model utility and relies entirely on model-generated data and requires no human annotation, representing a post-deployment hallucination mitigation framework.
Reach audiences
Advertise in front of researchers, engineers, and readers.
This analysis indicates that robust Long-Term Memory security cannot be retrofitted at retrieval or execution time alone, but must be anchored in storage-time provenance, versioning, and policy-aware retention from the outset.
This paper presents the first systematic audit between official LLM APIs and corresponding shadow APIs, and uncovers widespread behavioral inconsistency and fingerprint-based evidence consistent with deceptive model claims in a subset of audited endpoints.
We propose a system for marking sensitive or copyrighted texts to detect their use in fine-tuning large language models under black-box access with statistical guarantees. Our method builds digital ``marks'' using invisible Unicode characters organized into (``cue'', ``reply'') pairs. During an audit, prompts containin...
FedNIA injects random noise inputs to analyze the layerwise activation patterns in client models leveraging an autoencoder that detects abnormal behaviors indicative of data poisoning and can defend against diverse attack types, including sample poisoning, label flipping, and backdoors.
A2M (Attraction-to-Manipulation), a two-stage black-box framework for hijacking MCP agents, is introduced, a two-stage black-box framework for hijacking MCP agents that motivate stronger tool vetting and runtime isolation in MCP ecosystems.
It is argued that compile rate is a scientifically unreliable metric for single-function vulnerability repair, and this is supported with five controlled experiments over 203 vulnerable functions from Big-Vul, three open-source code LLMs (350M to 6.7B parameters), and three prompting strategies.
A methodology to systematically analyze and dissect existing approaches to define and enforce policy found in the wild is proposed to define and enforce policy found in the wild in GenAI applications.
It is found that Astra exhibits token-efficient directed reasoning, selecting a correct trajectory earlier, while resolving elementary steps internally and externalizing only crucial reasoning, which provides a behavioral lens on frontier-model reasoning beyond benchmark scores.
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.
