SRE-Bench is introduced, the first realistic, contamination-free RE benchmark, and results indicate that strong source-code security capabilities do not yet transfer to binary analysis, highlighting RE as an important frontier for agentic cybersecurity and SRE-Bench as a rigorous testbed to measure progress.
J. Spence, Nicholas Assaderaghi, Feng Xiao et al.· 1 citation
This work presents a security-oriented framework for risk identification, evaluation, and mitigation in a multi-agent GIS system while maintaining adaptability to broader agentic architectures.
K. Gao, Pranavi Kotta, Linlin Xu et al.· IEEE Geoscience and Remote S...· 0 citations
A trust-aware post-routing framework is proposed that reweights clients using returned-evidence feedback, including retrieval relevance, profile consistency, and cross-client agreement, and online experiments show that it suppresses persistent hijacking over recurring queries and transfers to a learned neural router.
BEACON is an LLM-driven framework for cross-source CTI knowledge graph construction that constructs and releases two human-annotated datasets from 34 sources and outperforms all baselines by at least 23% and 9%, respectively.
CamoDocs is proposed, a poisoning attack that avoids direct query inclusion by camouflaging adversarial documents among benign content, and shows that erasure-heavy clustering defenses such as TrustRAG can reduce ASR, but only with substantial utility drops on retrieval-dependent benchmarks such as NeoQA.
Jaewon Jung, Hai-Zhong Zheng, Hongsun Jang et al.· 1 citation
This work forms sector-targeted CTI dissemination as a multilabel classification problem, leveraging deep field knowledge of CTI structures and sector-specific threat patterns, and applies BERT, a transformer-based model, to automate the mapping of CTI events to sectors.
Fajar Wijitrisnanto, Alsharif Abuadbba, Yan-Song Gao et al.· 0 citations
This work develops GREAT, a novel framework for crafting natural distributional backdoors in RLHF, which targets harmful response generation for a vulnerable user subpopulation featured by semantically violent requests paired with emotionally angry triggers.
Subrat Kishore Dutta, Yuelin Xu, P. Pant et al.· arXiv.org· 0 citations
The exact DP constant is pin down for the two that carry the practical weight, counterfactual memorization and adaptive extraction, and it is shown that they do not control each other.
This work presents Replicant, a deep reinforcement learning framework that learns the realistic task of evasion under a strict label-only black-box threat model and demonstrates that learning the task of evasion not only results in stronger attack performance but provides a better signal for hardening malware detectors...
Shae McFadden, Ilias Tsingenopoulos, Mario D'Onghia et al.· 0 citations
LoopHarness is presented, which restores a persistent, non-decaying safety state at the loop level at the loop level, and gives a complete evaluation protocol on native Agent-SafetyBench tasks with paired clean and attacked episodes, an outer-state attack suite whose decisive evidence exists only across iterations, per...
This work identifies a critical gap: when unauthorized tools are visible in an agent's context, models select them in 48-68% of adversarial scenarios, even when explicitly instructed not to, and proposes a proxy-enforced attribute-based access control layer for MCP that filters tool registries at discovery time.
This work presents SkillSafetyBench, a runnable benchmark for evaluating skill-facing safety failures, and suggests that agent safety depends not only on model-level alignment, but also on how agents interpret skills, trust workflow context, and act through executable environments.
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.
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.
