Graph-structured data underpin a wide spectrum of modern applications, yet their multiple sensitive attributes are not isolated but deeply coupled with graph topology. This coupling facilitates intersectional privacy leakage through attribute inference attacks (AIAs). Existing AIAs predominantly assume adversaries with...
Passwords remain the dominant online authentication mechanism, and understanding how humans choose them is essential for defensive strength estimation and attack simulation alike. Recent learning-based approaches such as PassGAN and PassGPT have shown that deep generative models can learn password structure directly fr...
Certifying a deployed neural network raises decision problems that the verification literature has not classified: whether the model carries a backdoor planted in its training data, whether a fault in its stored parameters can drive it into an unsafe state, whether its output leaks a private part of its input. We forma...
Edge computing has emerged as a critical computing paradigm in modern distributed systems by migrating data processing closer to end users and Internet of Things (IoT) devices. While this paradigm decentralizes processes, minimizes latency, and reduces backhaul bandwidth congestion, it exponentially enlarges the cybera...
Zawad Yalmie Sazid, Robert Abbas· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Differentially private (DP) text generation can protect individual records, but privacy alone does not specify what evidence a released statement carries about the underlying data. We identify this as an evidence gap: a private report may contain plausible claims without indicating whether they are strongly supported b...
In personalized AI applications, such as conversational assistants and recommender systems, users interact not with models in isolation but with broader systems that access, infer, and reuse user information across components and over time. While such use of user information is integral to personalization, it also rais...
Advancing beyond traditional static scoring models, LLM-powered agentic recommender systems (LLM-ARS) instantiate users and items as autonomous agents, whose semantic states are dynamically refined through a recurrent process known as collaborative reflection. While this mechanism improves recommendation quality, it si...
Yu-Rong Hao, Wen Zhou, Guo-Wei Guan et al.· 0 citations
A structural causal model (SCM) is introduced that generates a realistically grounded, labelled dataset of user-sessions, with coordinated multi-account campaigns, platform feedback, and three tiers of label observability.
Manifold Anchored Bilevel Transfer (MABT), a unified framework that anchors adversarial trajectories to the shared semantic subspace, is proposed, and a Hessian-free solver with linear-time complexity is developed to handle the resulting hierarchy.
Sparse attention is widely used to accelerate long-context inference in modern large language models (LLMs), but its input-dependent execution behavior introduces previously unexplored privacy risks. We identify a new GPU micro-architectural side channel, termed Sparsity-Induced Memory Access (SIMA), which arises from...
Fahao Chen, Linkang Du, Jinhao Zhou et al.· 0 citations
Prompt-injection benchmarks for LLM agents typically test attacks through a single injection surface and report the resulting attack success rate as a property of the model. We ask whether those robustness conclusions remain stable when the same adversarial content enters through a different part of the agent interface...
Syed Nazmus Sakib, Nafiul Haque, Shahrear Bin Amin et al.· 0 citations
Relay and reseller APIs mediate access to large language models (LLMs), but users cannot directly verify which model serves them. We introduce \name, a black-box auditing protocol based on stable factual recall near the knowledge boundary, including repeatable wrong answers. KBF generates benign, renewable probes and c...
Yijia Fang, Yiqing Feng, Bingyu Li et al.· 0 citations
