EvoSherlock: Towards Agentic Lifelong Evolution for Unseen Long-Tailed...
arXiv:2609.19201v1 Announce Type: new Abstract: Existing Security-oriented Video Understanding (SVU) systems assume a \emph{closed world}, \ie static category sets, abundant labels, and the premise...
View ArticlePAPC: Platform Mediation for Privacy-Propagation Externalities in AI-Mediated...
arXiv:2609.19226v1 Announce Type: new Abstract: AI-mediated platforms coordinate work through LLM agents acting for different principals. In these workflows, privacy loss can be created before a final...
View ArticleRobust Conformal Intrusion Detection via Traffic-Aware Calibration and...
arXiv:2609.19241v1 Announce Type: new Abstract: Large language models fine-tuned for network intrusion detection emit single-point predictions without statistical validity guarantees. Conformal...
View ArticleAUDITPLAN: Commit, Then Answer for Auditable Safety Alignment
arXiv:2609.19325v1 Announce Type: new Abstract: Safety tuning pipelines judge only the final answer, which makes it difficult to distinguish robust refusal from two undesirable shortcuts: blanket...
View ArticleScaling Zero Knowledge UNSAT Verification via Normalized Chaining
arXiv:2609.19353v1 Announce Type: new Abstract: Proofs of UNSAT are a standard primitive in formal verification and software assurance. In many real-world settings, the proof itself encodes proprietary...
View ArticleBeyond Private Training: The New Landscape of AI Privacy
arXiv:2609.19456v1 Announce Type: new Abstract: Retrieval-augmented systems increasingly rely on vector indexes that may retain deleted items in their search graph. Existing deletion interfaces can...
View ArticleRed-Teaming Auto Mode: Improving Blocking Classifiers Against Malign Coding...
arXiv:2609.19587v1 Announce Type: new Abstract: To keep coding agents from going off the rails, production systems now review each proposed action with a blocking monitor that can reject it before it...
View ArticleSoK: Trading Agents or Market Crashers? Dissecting Robustness and Security...
arXiv:2609.19705v1 Announce Type: new Abstract: Autonomous large language model (LLM) agents are moving rapidly into high-stakes domains, yet existing agentic-AI security studies remain largely...
View ArticleReachability, Not Observation: Containing Systems Whose Wiring Changes
arXiv:2609.19720v1 Announce Type: new Abstract: Containment decisions -- where to put a firewall, which links to monitor, what a program may reach -- are computed from an observed structure, and...
View ArticleALIBI: Adversarial Legitimacy Injection in Binary Input against LLM Malware...
arXiv:2609.19722v1 Announce Type: new Abstract: Large language models are being integrated into malware triage workflows as reasoning components that summarize static evidence and produce...
View ArticleSybil-TraceGuard: Traceability-enhanced Sybil Guardian for Connected and...
arXiv:2609.19791v1 Announce Type: new Abstract: Connected and autonomous vehicles (CAVs) face severe Sybil attacks, where attackers exploit privacy-preserving pseudonym-switching mechanisms to anomaly...
View ArticleTrust, but Validate the Instrument: Auditing AI-Generated RTL Verification...
arXiv:2609.19844v1 Announce Type: new Abstract: AI-generated RTL verification plans can satisfy a provider schema yet fail at the boundary to trusted execution. We present SecTB-RTL, an auditable...
View ArticleClashBench: Conflicts Leading Agents to Seize and Harm
arXiv:2609.19892v1 Announce Type: new Abstract: As agent systems become more widely used, multiple agent sessions increasingly run alongside pre-existing user tasks in the same environment, sharing...
View ArticleHopper: Bounded-Memory Collaborative Debiasing for Byzantine-Tolerant Peer...
arXiv:2609.19893v1 Announce Type: new Abstract: Byzantine-tolerant peer sampling relies on continuously refreshed views, yet an adversary can bias the identifier streams used to construct them....
View ArticleDelphi Scanner: efficient and interpretable static malware detection via API...
arXiv:2609.19900v1 Announce Type: new Abstract: Static malware detection for Windows Portable Executable files demands a careful balance between detection effectiveness, computational efficiency, and...
View ArticleMind the Gap: How SBOM Specification Ambiguities Lead to Divergent Software...
arXiv:2609.19920v1 Announce Type: new Abstract: Software Bill of Materials (SBOMs) will become mandatory starting in December 2027 under the European Cyber Resilience Act (CRA) [8]. Although previous...
View ArticleOn the Leakage of Massey Secret Sharing Schemes under Linear Computations
arXiv:2609.19929v1 Announce Type: new Abstract: Leakage attacks on secret sharing schemes exploit partial information about individual shares to recover the underlying secret. In coding theory, linear...
View ArticleJANUS: Denial-of-Service Attack Against Beam Hopping in LEO Satellite Networks
arXiv:2609.19977v1 Announce Type: new Abstract: Low Earth orbit (LEO) satellite networks are increasingly used to provide global connectivity. However, each satellite has limited resources that need to...
View ArticleXIR: A Framework for Interoperability across Cross-Chain Protocols Based on a...
arXiv:2609.20010v1 Announce Type: new Abstract: Cross-chain protocols enable applications to exchange messages across blockchains. Under point-to-point configurations, communication depends on a direct...
View ArticleCompetition, Collusion, and Corruption: The Spectrum of MEV Attacks on...
arXiv:2609.20069v1 Announce Type: new Abstract: Byzantine Fault-Tolerant (BFT) protocols guarantee safety and liveness despite the malicious failure of nodes. However, they do not prevent adversarial...
View Article