AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
Category
1,407 papers
Models are usually aligned based on their observed outputs, using demonstrations, preference data, or reward signals. These objectives reward responses that look aligned. More capable models may learn to satisfy them without internalizing the intended behavior, for example by faking compliance during training. Such sup...
Large language models (LLMs) incur substantial storage, memory-bandwidth and energy costs, motivating compact weight representations. Existing seed-based compression methods reconstruct weights from compact pseudo-random representations but do not explicitly account for the non-uniform sensitivity of model weights. We...
This technical report presents an alignment evaluation developed and performed by the UK AI Security Institute for assessing whether advanced AI systems take unsanctioned actions outside the scope of their assigned task. We evaluate whether frontier models conduct supply-chain attacks against out-of-scope, third-party...
AI-enabled Cyber-Physical Systems (CPS) are highly vulnerable to adversarial and anomalous inputs, where small perturbations can induce cascading errors and unsafe control actions. Existing approaches, such as rule-based filtering, training-time regularization, or diffusion-based reconstruction, either operate outside...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Aegis is proposed, a principled client-side defense that breaks this dilemma without perturbing patient data or modifying the FL protocol, offering a practical privacy primitive for medical FL.
This work evaluates Janus under crash injection, by verifying a 100-million-event log offline, and with a real model behind a lending workflow, run governed and plain on the same recorded model outputs.
Text-to-image (T2I) models have substantially improved in language understanding, in-image text rendering, and visual composition, while their safety mechanisms do not always keep pace with these capabilities. This creates a cross-modal attack surface in which harmful semantics can remain inconspicuous in a serialized...
This work introduces the first continual learning framework for IFL and establishes a comprehensive benchmark under two realistic data-evolution protocols: cross-dataset and cross-content continual learning.
ModalFidelity, a lightweight router that previews each window and decides, before any forensic detector runs, which stream is worth reading, under a hard compute budget it can never exceed, is presented.
A common framework in which each attempt ends in approved completion, safe stopping, scope escape, or continuation is introduced, which formalizes the framework as a discrete-time competing-hazards model and derive escape probability within a retry budget, a model-conditional safe-budget limit, and conditions for estim...
Reliable provenance for LLM outputs requires multi-bit watermarks that remain robust under editing while maintaining low false-positive rates. Existing ECC-based LLM watermarks rely on hard-decision decoding, discarding token-level reliability information and limiting robustness under post-generation edits. We propose...
Tandem Token WaterMark (TTMARK), a general pairwise watermarking framework that extends distortion-free watermarking from individual tokens to adjacent token pairs, and introduces a branch-isolating concatenated tandem generation algorithm that efficiently constructs the joint distribution in a single forward pass.
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.
