cs.CR · 2026-10-07 · No. 136
Cryptography and Security, 2026-10-07.
8 new papers in cs.CR. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
8 entries-
01
Secure Speculative Decoding for Large Language Models
Yichi Zhang, Zhiqi Wang, Neil Gong, Yuchen Yang
cs.CR · cs.AI · cs.LG
Speculative decoding accelerates inference for a large language model (LLM), referred to as the \emph{target model}, by first using a smaller model, referred to as the \emph{draft model}, to generate candidate tokens and then verifying them with the target model for acceptance or rejection. Prior studies primarily focused on the efficiency-utility trade-off of speculative decoding, e.g., lossy speculative decoding, leaving its security...
-
02
Semantic Behavioral Watermarking: Paraphrase-Robust and Forgery-Resistant Provenance for LLM Agents
Suxin Ji, Hungtao Wan, Shaoxuan Chen, An Zhang
cs.CR · cs.AI
Behavioral watermarking embeds an owner identifier in an LLM agent's high-level action choices, giving provenance without touching output tokens. Prior agent watermarks break in two ways. First, all three prior schemes bind the watermark to the exact action symbol, so renaming a tool desynchronizes decoding even when the observation is untouched; in AgentMark's own robustness test, paraphrasing the observation alone drops bit-recovery to...
-
03
RAG-PIBench: A Leakage-Aware Benchmark for Prompt-Injection Detection in Trustworthy RAG Systems
Niveen O. Jaffal, Ahmet Yuksel, David Mohaisen
cs.CR · cs.AI · cs.LG
Retrieval-Augmented Generation (RAG) systems are vulnerable to prompt-injection attacks embedded in retrieved content. We introduce RAG-PIBench, a benchmark for RAG-style prompt-injection detection containing 4,876 contextual examples across frozen train, validation, and protected-test splits. Using a leakage-aware construction pipeline and strict evaluation protocol, we compare keyword-based, semantic-reference, TF-IDF, and transformer-based...
-
04
MARCO: The Radioactive Watermark for Protein Generative Models
Huajie Chen, Xin Guo, Yuchen Shi, Yuchen Zhong, Minhui Xue, Chi Liu, Congcong Zhu, Kun Gao, Minfeng Qi, Tianqing Zhu
cs.CR · cs.AI
Protein Generative Models (PGMs) have revolutionized structural biology by enabling the design of complex 3D protein structures from sequence data. However, this breakthrough introduces a dual-use challenge, exposing high-value PGMs to economic risks like unauthorized model extraction and biosecurity threats such as biohazard synthesis. To mitigate these threats, we propose \textbf{MARCO} (\textsc{COnformation waterMARk}), the first...
-
05
Contextual Chain: Lightweight Continuity Authentication for Intermittently Connected Devices
Song-Ju Kim
cs.CR · cs.DC
Can authentication make memory, rather than computational hardness, the attacker's bottleneck? Contextual Chain is a lightweight continuity protocol for intermittently connected devices that share evolving physical or operational context. An honest device follows one realized history, updating a compact accumulator and fixed hash-based readiness lanes; outages cause pause or bounded rollback, not branch search. After the epoch is frozen, a...
-
06
Surviving the Router: Optimizing Skill Injections for Retrieval and Execution
Haneen Najjar, Luca Scionis, Haritz Puerto, Sahar Abdelnabi
cs.CR · cs.LG
AI agents increasingly rely on modular third-party "skills" that are dynamically selected by skill routers to execute complex tasks. While recent studies highlight the threat of prompt injections embedded in these skills, existing evaluations often assume settings where the malicious skill is already selected for execution. We show that this assumption can substantially overestimate attack success. In realistic multi-skill environments,...
-
07
When Tools Lie: Reliability of Mathematical Agents Under Corrupted Tool Feedback
Kavienan Jegatheesan, Gayathri Lihinikaduarachchi
cs.CR · cs.AI · cs.SE
Mathematical problem solving often requires deterministic computational steps that agents delegate to tools and implicitly trust. Yet tools can fail silently, returning plausible but incorrect results. How well can agents detect and correct corrupted tool call outputs? We study this through a controlled corruption framework where a hidden interceptor replaces tool call results with plausible incorrect information on targeted problems. We...
-
08
Explainable Rule Mining of IPv6 Extension-Header Presence Patterns from Paired-Vantage Captures
Priyanka Sinha, Nikolaos Kekatos, Stylianos Basagiannis, Antonio Anastasio Bruto da Costa, Alexios Lekidis, Pabitra...
cs.CR · cs.LG · cs.NI
IPv6 extension headers (EHs), such as fragmentation, segment routing, and in-situ telemetry, are operationally important yetwidely dropped in transit, and characterising their behaviour from packet captures is a recurring measurement problem. We ask whetheran explainable miner can recover human-readable rules of EH behaviour, and we contribute two reusable tools: a negative-control protocol that diagnoses whether a mined "temporal" network...
This edition is part of The Daily Abstract — cs.CR archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.