AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
Category
1,407 papers
The Static-Pass Dynamic-Fail (SPDF) phenomenon and a three-stage agentic pipeline combining static scanning, LLM-driven Common Weakness Enumeration (CWE) reasoning, and autonomous exploit verification in isolated Docker containers are introduced.
A novel neurosymbolic defense-in-depth architecture that ensures end-to-end pipeline integrity and dismantles the promptware kill chain, bounding LLM stochasticity with verifiable constraints, and delivering a resilient, highly observable defense mechanism for next-generation AI-SOCs.
By distilling a lightweight model Veilmind-4B to drive a dynamic extraction-sanitization-restoration pipeline, this approach reaches a low-leakage privacy point while preserving substantially higher response utility than existing privacy-oriented baselines, advancing the privacy-utility trade-off toward the Pareto fron...
SpecGuard is introduced, an inference-time backdoor detector that repurposes speculative decoding at zero added model-computation cost and doubles as a free, always-on signal for detecting backdoored LLM behavior.
Reach audiences
Advertise in front of researchers, engineers, and readers.
SAC-Copula is proposed, a quality-preserving watermarking method for DLMs based on smooth, locally correlated Gumbel perturbation fields constructed via a Gaussian copula that substantially improves PPL tail stability over the i.i.d. Gumbel baseline while maintaining strong low-FPR detectability and competitive overall...
The initial feasibility of end-to-end mmWave sensing under FHE on commodity hardware is established and two cryptographic guarantees for any pipeline assembled from this library are formally proved: input privacy and data obliviousness.
Deep neural networks (DNNs) rely heavily on high-quality open-source datasets (e.g., ImageNet) for their success, making dataset ownership verification (DOV) crucial for protecting public dataset copyrights. In this paper, we find existing DOV methods (implicitly) assume that the verification process is faithful, where...
In a simulator for COVID19, even at epsilon=1 per message, this work can significantly improve the detection of potentially infected individuals and, as a result of targeted testing, reduce infection rates.
The results show that differentially private perturbation can be integrated into EEG processing workflows, but the selected mechanism, privacy parameters, and sensitivity calibration strongly influence data utility.
The results separate indiscriminate poisoning, which shows up in standard metrics, from targeted backdoor poisoning, which stays comparatively stealthy while embedding highly effective malicious behavior, and they support security-oriented evaluation beyond conventional clean-test metrics.
A controlled benchmark of membership inference vulnerability for text classification on the GLUE SST-2 sentiment dataset is presented and lightweight training adjustments can improve the privacy-utility trade-off without complex defenses.
DriftNet is presented, a dual-head trajectory Transformer that reads a logged tool-call trajectory and answers all three questions in one forward pass: one head classifies the trajectory as compromised or not, and a second assigns every step one of four labels (benign, injection point, hijacked, failed injection).
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.
