A novel method, namely Fractal-Triggerred Distributed Backdoor Attack (FTDBA), which leverages the self-similarity of fractals to enhance the feature strength of sub-triggers and hence significantly reduce the required poisoning volume for the same attack strength is proposed.
Jian Wang, Hong Shen, Chan-Tong Lam· arXiv.org· 0 citations
PiMRef is proposed, the first reference-based solution to detect ever-evolving phishing emails using knowledge-based invariants, targeting the identity-impersonation attacks that characterize spear-phishing.
Ruo-Fan Liu, Yun Lin, Yu-Xin Wang et al.· 4 citations
The results demonstrate that a clean teacher alone is not a sufficient safeguard: poisoned distillation data can produce a strongly backdoored student while maintaining competitive performance on clean images.
Machine unlearning is a promising approach to improve LLM safety by removing unwanted knowledge from the model. However, prevailing gradient-based unlearning methods suffer from issues such as high computational costs, hyperparameter instability, poor sequential unlearning capability, vulnerability to relearning attack...
Aashiq Muhamed, Jacopo Bonato, Mona Diab et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Malicious users attempt to replicate commercial models functionally at low cost by training a clone model with query responses. Timely prevention of such model-stealing attacks is challenging, as it requires achieving robust protection, maintaining utility, and ensuring low deployment overhead at the same time. In this...
Jian-Ping Mei, Weibin Zhang, Jie Chen et al.· 0 citations
Large Language Models (LLMs) face significant security risks despite their advanced capabilities. While techniques like Reinforcement Learning with Human Feedback (RLHF) improve ethical alignment, excessive exposure to security-related training data may cause LLMs to overtrust such information, creating new vulnerabili...
AHLERT is introduced, a system that automatically extracts relevant, environment-aware, and hunt leads from threat reports through a hybrid retriever that combines dense vector search with multi-hop traversal over a knowledge graph seeded with MITRE ATT&CK.
A. Prakash, Boubakr Nour, M. Pourzandi et al.· 0 citations
This work audits eight cybersecurity benchmarks across 10 proprietary, open-weight, and cybersecurity-specialized LLMs and shows that cybersecurity LLM benchmark scores are pipeline-dependent and motivate pipeline-aware auditing as a core requirement for reliable model evaluation.
Aymene Berriche, Cathrine Shalby, Mohannad J. Alhanahnah et al.· 1 citation
A platform that connects a pluggable red-team adapter and a pluggable blue-team adapter to a shared target LLM and scores their attack and defense rates with an LLM judge, and describes the design of ACEA and the metrics through which red and blue teams are scored head to head.
Yi-Da Shen, Kentaroh Toyoda, Alex Leung· 0 citations
A controlled study on six open-source research software projects, with protocol, seed, panel, and analysis plan deposited with a DOI before any trial, drew three conclusions: publishing signals is necessary but not sufficient; price did not buy verification; verification must be built into the program that runs the ass...
Repeated runs show that category-level and within-trajectory relations can recur even when normalized score-change rankings do not, and motivate agent-behavior evaluation that links communication, authorization, and evolving state instead of treating individual transaction verdicts as complete safety judgments.
Ze-Lin Li, Yi-Yun Su, Matt White et al.· 0 citations
Intentest is proposed, an intent-graph-guided automated penetration testing agent that externalizes long-horizon state from the LLM's context window onto a persistent fact-intent directed acyclic graph (DAG), thereby substantially reducing invalid transitions.
Wei-Zhe Wang, Yi-Tong Zhang, Yao Zhang et al.· 0 citations
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.
