North Korean defectors residing in China face persistent uncertainty regarding digital security and privacy. Through semi-structured interviews with 19 defectors, we examine how individuals understand digital threats and adapt their security behaviors. We identify three interrelated conditions: transnational surveillan...
Yibo Meng, Bingyi Liu, Lionel Z. Wang et al.· 0 citations
LLM-agents In-OS Testing for Measuring Unsafe Subversion is presented, a benchmark addressing both gaps via a semantic-physical dual verification mechanism and OS-level state rollback and providing the first standardized platform for reproducible, physically grounded behavioral safety evaluation of LLM agents in real O...
Chiyu Zhang, Lu Zhou, Xiao-Gang Xu et al.· arXiv.org· 7 citations· ⚡2
As backdoor attacks become more stealthy and robust, they reveal critical weaknesses in current defense strategies: detection methods often rely on coarse-grained feature statistics, and purification methods typically require full retraining or additional clean models. To address these challenges, we propose DUP (Detec...
Man Hu, Yahui Ding, Yatao Yang et al.· 0 citations
Watermarking has great potential for regulating the use of language models (LMs), but its deployment has been marred by controversy, as many users argue that fine-grained tracking of LM usage violates their privacy. This tension reduces the effectiveness of watermarks, as users engage in evasion strategies such as para...
Elise L. Han, Tatsunori Hashimoto· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Semantic communication (SemCom) using a relay node is considered, where the relay assists in conveying task-relevant information from a source to a destination, with meaning defined by classification labels. A joint end-to-end design of the source encoder, relay transformation, and destination decoders is developed to...
Yalin E. Sagduyu, Tugba Erpek, Aylin Yener· 0 citations
Nowadays, large language models produce text at scale, and much of it is redistributed across platforms. A moderator who finds a suspicious comment, post or article may want to know which platform generated it and for which account. In this paper we study attribution over the channel through which such text actually tr...
Andrei Alexandru Dr\u{a}ghici, Sediola Ruko, Briland Hitaj et al.· 0 citations
A taxonomy of AI slop grounded in a structured literature review is formalized and a roadmap for securing emerging AI-driven triage systems is provided, shifting evaluation from linguistic fluency to mathematical verifiability.
Junchen Ding, Jialiang Dong, Yi Zhu et al.· arXiv.org· 0 citations
Fine-tuning large language models on narrow data with harmful content produces broadly misaligned behavior on unrelated prompts, a phenomenon known as emergent misalignment. We propose that emergent misalignment involves persona-model collapse: a deterioration of the internal representations that encode and distinguish...
D. B. Costa, Renato Vicente· arXiv.org· 3 citations
Large language models (LLMs) are highly compute- and memory-intensive, posing significant demands on high-performance GPUs. At the same time, advances in GPU technology driven by shrinking transistor sizes and lower operating voltages have made these devices increasingly susceptible to soft errors, particularly in radi...
Duo Chai, Zizhen Liu, Shuhuai Wang et al.· 0 citations
Federated learning servers combine client models with a fixed aggregation rule, and each rule in common use is designed for one kind of heterogeneity. We study whether a large language model (LLM) that inspects the client models can choose the rule itself, without any training on the server. In FedReason, the LLM is ca...
Ali Mohammadi Ruzbahani, Abbas Yazdinejad, Hadis Karimipour· 0 citations
Indirect prompt-injection (IPI) benchmarks predominantly test planted instructions that redirect a tool-using agent toward an attacker-chosen task. Yet attacker-controlled content can instead tamper with the outcome of the task already in progress. A buyer's dispute evidence can cite a false refund policy to inflate a...
Rongting Zhang, Martin Bertran, Sandeep Avula et al.· 0 citations
Enterprise AI agents increasingly split a user's request across subagents and merge their results, and each handoff can summarize away, alter or ignore a requirement. We report a preregistered study with synthetic, exactly scorable tasks comparing free-text, structured JSON and signed requirement-manifest handoffs: the...
Xiaobo Chen, Genliang Zhu, Ziyuan Wang 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.
