A comprehensive review of the modern threat landscape targeting Voice Authentication Systems (VAS) and Anti-Spoofing Countermeasures (CMs), including data poisoning, adversarial, deepfake, and adversarial spoofing attacks is presented.
This paper presents DF-CAPTCHA, an active defense against real-time deepfake impersonation in voice and video calls. Instead of passively searching for artifacts, DF-CAPTCHA prompts the caller to perform simple challenge-response tasks that are easy for humans but difficult for current real-time deepfake systems to gen...
Guy Frankovits, Lior Yasur, Fred M. Grabovski et al.· 0 citations
This work specifies terms.txt, a robots.txt-style file for per-path, per-purpose machine-access terms, plus an origin-enforced exchange using Web Bot Auth signatures, signed intent, delegation tokens, HTTP 402 negotiation, and signed receipts, and defines what the exchange can enforce, audit, and leave to contract.
BenchShield is presented, a model-backed instrumentation layer for reward integrity in LLM-agent evaluation that grounds detection in a finite lifecycle model of an evaluation's reward-relevant events and achieves 96% accuracy in detecting reward hacking from infrastructure-side evidence.
Sheng-Han Zheng, Zong-Lin Di, Yimin Liu et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
DeFiFusion is presented, a dual-modal PMA detection framework that closes this gap by jointly modeling transaction events and smart contract semantics within a unified pipeline, and proposes a Dual-Modal Projection-Fusion Transformer with T5-style relative positional encoding.
Rui Cao, Shao-Jing Fan, Li-Ming Fang et al.· 0 citations
This work proposes a new paradigm of no-box vulnerability analysis in which neither access nor runtime interaction is available, and only functionality metadata is available, and introduces no-box vulnerability analysis as a new analysis paradigm and demonstrates its practical feasibility in realistic systems.
Ze-Hua Zhang, Jie Hu, Pratham Hegde et al.· 0 citations
The Static-Pass Dynamic-Fail (SPDF) phenomenon and a three-stage agentic pipeline combining static scanning, LLM-driven Common Weakness Enumeration (CWE) reasoning, and autonomous exploit verification in isolated Docker containers are introduced.
Jessica Pourleyli, Maitreyee Das Urmi, Glaucia Melo· 0 citations
The integration of Large Language Models (LLMs) into Security Operations Centers (SOCs) streamlines threat intelligence but introduces critical vulnerabilities, notably indirect prompt injection via log poisoning. Adversaries exploit this vector to execute multistep ``promptware'' kill chains by embedding malicious pay...
Anna Gazani, Spyridon Kounoupidis, Panagiotis Katsaros et al.· 0 citations
By distilling a lightweight model Veilmind-4B to drive a dynamic extraction-sanitization-restoration pipeline, this approach reaches a low-leakage privacy point while preserving substantially higher response utility than existing privacy-oriented baselines, advancing the privacy-utility trade-off toward the Pareto fron...
Zhenhua Liu, Zhan-Xu Xie, Junjie Yu et al.· 1 citation
SpecGuard is introduced, an inference-time backdoor detector that repurposes speculative decoding at zero added model-computation cost and doubles as a free, always-on signal for detecting backdoored LLM behavior.
Wen Rui, Ahmed Salem, Andrew Paverd et al.· 0 citations
Watermarking diffusion language models (DLMs) requires mechanisms compatible with iterative parallel unmasking rather than autoregressive decoding. Existing sampling-based watermarking methods typically inject position-wise i.i.d. perturbations, which can be poorly aligned with DLM decoding dynamics and degrade generat...
The initial feasibility of end-to-end mmWave sensing under FHE on commodity hardware is established and two cryptographic guarantees for any pipeline assembled from this library are formally proved: input privacy and data obliviousness.
Tanvir Ahmed, Yixuan Gao, A. Armouti et al.· arXiv.org· 0 citations