cs.CR · 2026-08-26 · No. 96
Cryptography and Security, 2026-08-26.
4 new papers in cs.CR. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
4 entries-
01
Not All Tokens Are Equal: Region-Aware Consistency Repair of Backdoors in MLLMs
Jiali Wei, Ming Fan, Mingkun Zhang, Haoyu Wang, Jun Sun, Guoheng Sun, Xiaoning Ren, Haijun Wang, Ting Liu
cs.CR · cs.AI · cs.CL
MLLMs are increasingly deployed in user-facing applications, yet they inherit backdoor risks from the pipelines used to construct them: triggers may reside in images, texts, or both. Existing model-level backdoor removal methods, largely designed for conventional classifiers, show limited effectiveness on MLLMs, while MLLM-specific defenses mainly operate at inference time, filtering suspicious inputs without removing the backdoor embedded in...
-
02
Anatomy of a Scam Call: What 10,000 real scam and spam calls reveal about how phone scammers operate
Ethan Traister, Ankit Raj, Jiaqi Gan, Xingyu Shen, Tyler Wu, Yuchen Zhou, Tommy Duong, Kidus Zewde, Siying Chen, Simiao Ren
cs.CR · cs.CL · cs.CY · cs.LG
Telephone fraud is pervasive and costly, but its inner workings are rarely observed at scale. We analyze a complete corpus of 10,211 inbound scam and spam calls -- 913 hours of audio and 330,956 transcribed turns from 5,780 distinct numbers -- collected over 54 days by an AI voice-agent honeypot that answered callers and kept them talking, and introduced in a companion data descriptor. We separate outright scams, which solicit sensitive...
-
03
What Guides the Agent? Adjudicating Unauthorized Behavior via Localizing Behavior-Guiding Instructions
Yichao Gao, Yumo Zhang, Yunhao Yao, Haohua Du, Puhan Luo, Ruiqi Li, Zhiqiang Wang
cs.CR · cs.AI
LLM agents integrated with external resources gain complex task capabilities, yet the unified natural-language context channel makes them vulnerable to injection attacks: untrusted external data may be dynamically parsed as behavior-guiding instructions during LLM inference, thereby subverting the agent's decision. Existing defenses focus on static detection or isolation of malicious content at the input/output level, remains insufficient for...
-
04
WebMCP-Phalanx: Enforcing and Characterizing Trust Boundaries for Browser-Integrated LLM Agents
Lin-Fa Lee, YI-YU Chang, Kuo-Hui Yeh
cs.CR · cs.AI
The emerging W3C WebMCP proposal enables LLM agents to invoke tools exposed by web pages. In multi-party web environments, however, integrating agent execution into a browser security model centered on the Same-Origin Policy (SOP) leaves insufficient provenance and lifecycle guarantees for agent-accessible tools, creating three risks: subject-attribution spoofing, uncontrolled tool lifecycles, and semantic prompt injection. We propose...
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.