A secure adaptive framework for authentication in multi-zone networks (SAFA-MZ), a causal meta-learning framework for distributed PLA (DPLA) in NTNs, and a model-agnostic meta-learning strategy with invariant risk minimization (IRM) and causal consistency regularization for fast adaptation to unseen NTN environments wi...
Parsa Rajabi, M. Abedi, N. Mokari et al.· 0 citations
This work presents MMPIBench, a reproducible benchmark that measures how far each injected instruction travels through the agent, from perception through planning to the tool call, and extends the benchmark to audio, the only other raw perceptual channel current frontier models accept.
Retrieval-augmented generation (RAG) grounds a language model in retrieved documents, which reduces hallucination but creates a new attack surface: if retrieved text is tampered with, the model may repeat the falsehood. We study how much a small quantized model, Llama 3.1 8B, degrades when a fraction of its retrieved c...
A conceptual defensive architecture separates evidence analysis, adjudication, and operational authority and connects coverage to fallible evidence checking, proper scoring of factual grounding, complete resource accounting, service capacity, and a response model that includes mitigation delay.
VG Jithin, PS Ditto· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This paper presents an end-to-end evaluation framework for image-triggered command injection against computer-use agents (CUAs). The goal is to test whether a local visual patch can induce verifiable environmental consequences along the full chain of screenshot input, VLM generation, action parsing, and environment exe...
Zhihao Liu, Hongyu Sun, Zhiyuan Fu et al.· 0 citations
Self-issued authentication as a conversational security failure is identified: authenticated identity must originate from an external security component, and model-generated dialogue must never create or modify identity or authorization state.
Cybersecurity incidents such as data breaches have become increasingly common, affecting millions of users and organizations worldwide. The complexity of cybersecurity threats challenges the effectiveness of existing security communication strategies. Through a systematic review of over 3,400 papers, we identify specif...
Carolina Carreira, Alexandra Mendes, Jo\~ao F. Ferreira et al.· 0 citations
A dual-assessment framework is introduced that scores any real-time gaze transformation on two axes at once: interaction utility, measured through an offline gaze-interaction simulation and an operational spatial-accuracy metric, and privacy preservation, measured through the Rank-1 Identification Rate of a state-of-th...
Mehedi Hasan Raju, Oleg V. Komogortsev· 3 citations
Across model-level safety on HarmBench and agent-level safety on AgentHarm, Membrane achieves the highest F1 on all six modern jailbreak attacks, and benign refusal on AgentHarm stays at 7-14%, well below the 28-85% range of prior guards.
Minseok Choi, Seung-Moo Yang, Dongjin Kim et al.· arXiv.org· 2 citations
Alarming misalignment in DR agents is demonstrated and underscore the urgent need for tailored alignment techniques: both the research role assignment and the multi-step execution mechanism weaken alignment of the base LLM, leading to severe safety breaches.
Shuo Chen, Zong-Gen Li, Xing-Yu Jin et al.· 2 citations· ⚡1
It is shown that reasoning-based guardrails are necessary but not sufficient and must be paired with robust triggering mechanisms and stronger base-model alignment, and develops four simple yet effective red-teaming methods that systematically subvert different stages of the guardrails.
Shuo Chen, Zhen Han, Haokun Chen et al.· 4 citations
This work proposes two classes of attacks: a static attack, which employs a fixed injection prompt, and an iterative attack, which optimizes the injection prompt against a simulated reviewer model to maximize its effectiveness.
Qing Zhou, Zhexin Zhang, Zhi Li et al.· arXiv.org· 6 citations· ⚡1
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.
