Category
1,065 papers
This paper presents Maverick, a novel approach to private and verifiable LLM inference based on a protocol for delegating matrix-vector multiplication, a dominant operation in LLMs, and combines this verification primitive with LPN-based pseudorandom masking to provide input privacy.
Average treatment effect (ATE) estimation in observational studies is a fundamental statistical tool used frequently in social science, medicine, and other fields. These fields often work with sensitive data where privacy protections are important, so a differentially private mechanism for ATE estimation is highly desi...
In network traffic, legitimate behaviours and attack techniques evolve jointly - the phenomenon known as 'concept drift' [1]. Every detector is thereby left obsolete between two updates, and always one step behind adversaries. In this work, we propose to move the point of intervention from the model, repaired after the...
Enterprises managing large X.509 certificate inventories face a prioritization problem: deterministic analysis tools that precisely identify standards violations are indispensable for remediation, but applying them exhaustively across millions of certificates is operationally impractical. We present X-amine509, a two-s...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Fully homomorphic encryption (FHE) enables inference on private data without revealing it to the server, but evaluating an entire input under FHE is expensive. We study \emph{selective homomorphic inference}, where only a sensitive region of interest (ROI) is encrypted, and computations independent of that region are p...
Results demonstrate that neuromorphic temporal encoding can provide both accurate cyber-attack detection and improved resilience to data poisoning in cyber-physical systems.
Chameleon is an openly distributed adaptive honeypot that integrates: a BiLSTM classifier achieving 99.61% accuracy across seven threat categories at ~2 ms CPU latency; a locally deployed Qwen3.5-0.8B model delivering 90% generation accuracy at 4.5 ms latency; and two meta-heuristic engines.
Generative models now write application code, harden and monitor it, and probe it for exploitable flaws, so that one family of models increasingly plays builder, defender and breaker at once. The prevailing view treats full autonomy as the natural end point of assistance. This article argues for a narrower and more def...
This paper presents a formal model of an OT intrusion response use case using the POMDP framework, which includes a realistic model of partial observability that is based on traffic measurements and allows for tractable, learning-based solution methods for automated intrusion response, which are based on PPO.
Large language models remain fragile against malicious fine-tuning, motivating training-time defenses against harmful persona drift. Preventative Steering injects undesirable-trait persona vectors during fine-tuning and removes them at evaluation time, yet the mechanism behind its lasting protection remains unclear. An...
A feasibility taxonomy of twenty inference-time mechanisms across monitoring, verification, and enforcement, each rated on a four-point readiness scale against a documented four-vendor evidence base is developed.
A controlled evaluation of adversarial transferability across 60 detectors spanning six backbones, two pretraining regimes, and five training-data configurations establishes source-model selection as central dimensions of credible transfer-based black-box robustness evaluation.
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.
