cs.CR · 2026-08-19 · No. 89
Cryptography and Security, 2026-08-19.
11 new papers in cs.CR. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
11 entries-
01
The Model's Tell: Measuring Context-Leakage Attack Signals with Behavior Gauges
Maosen Zhang, Jianshuo Dong, Boting Lu, Wenyue Li, Xiaoping Zhang, Tianwei Zhang, Jie Zhang, Han Qiu
cs.CR · cs.AI
LLMs increasingly rely on external contexts, such as pre-defined system prompts or retrieved documents, to improve generation quality. However, processing these contexts alongside user queries creates an attack surface: adversarial inputs can induce models to disclose them. Prior probing studies suggest that leakage-related signals emerge in hidden states, yet the need to extract these states poses additional deployment challenges. In this...
-
02
Diff-DDoS: Realistic Cyber-Physical Attack Synthesis and Robust Detection for 5G-Enabled CPS Using Tabular Diffusion Models
Bilal Hussain, Xiao Tang, Qinghe Du, Tan Li, Muhammad Azhar, Danista Khan
cs.CR · cs.LG
Deep learning-based DDoS detectors for 5G-enabled cyber-physical systems face scarce labeled attack data and unrealistic synthetic substitutes, which limit robustness against adaptive adversaries. Detectors trained on hand-crafted attacks with fixed scaling multipliers degrade catastrophically (F1-score drops of about 47 percent to 100 percent, depending on scenario) when confronted with realistic, distribution-preserving samples. We propose...
-
03
MemCatalyst: Amplifying Data Auditing on Vision-Language Models via Data Poisoning
Xukun Luan, Jinyan Liu, Yuhui Gong, Yuanguo Bi, Bing Hu, Xuesong Li, Di Wang
cs.CR · cs.LG
Vision-Language models (VLMs) achieve outstanding performance largely due to the amount of training data available on the internet. At the same time, data holders (e.g., artists) urgently need to determine whether their data has been used for model training without authorization, which concerns both intellectual property rights and personal privacy. Data auditing, particularly through membership inference (MI), has attracted attention as a...
-
04
MobileWorldSafety: Benchmarking GUI Agent Safety Against Environmental Injection Attacks in Android Apps
Sujin Chen, Lijun Li, Tianyi Du, Jing Shao
cs.CR · cs.AI
LLM-powered GUI agents that autonomously operate smartphones are rapidly transitioning from research prototypes to early real-world deployment. However, because these agents routinely process untrusted environmental content, they are highly vulnerable to environmental injection attacks, which include indirect prompt injections and adversarial instructions. Such attacks can manipulate the behavior of agents without user awareness through...
-
05
HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety
Yajing Bai, Jinhao Duan, Jie Peng, Xianfeng Wu, Sijia Liu, Song Wang, Tianlong Chen
cs.CR · cs.AI
Large language models are increasingly deployed through agent harnesses that manage tools, extensions, persistent state, permissions, and external actions. Existing safety benchmarks mainly target individual attack mechanisms or a limited subset of operational settings, making it difficult to compare how safety failures emerge across different harness responsibilities. We present HarnessRisk, a lifecycle oriented benchmark that organizes...
-
06
Reflex-Guard: A Low-Latency Guardrail for LLM Prompt Safety Using Dense Semantic Embeddings
Istiaque Ahmed, Afia Anjum Borsha, Ranat Das Prangon, Abu-fuad Ahmad, Thi Hong Tran
cs.CR · cs.CL · cs.LG
Large Language Models (LLMs) in real-world applications often face the risks of specially crafted prompts designed to bypass the safety controls. Existing guardrail methods, such as LLM-as-a-judge and cloud-based safety APIs are able to detect unsafe content. However, they often add a delay of about 250-900 ms to each request. This delay is too high for real-time applications, when the system usually needs to respond in less than 100 ms....
-
07
Fair ASR: Re-Evaluating Black-Box Jailbreaks under Shared Target-Call Budgets
Zhida He, Xiaoyu Wen, Han Qi, Ziyuan Zhou, Peng Yu, Jiajia Li, Chaochao Lu, Qiaosheng Zhang
cs.CR · cs.AI
Reliable jailbreak evaluation is essential for assessing LLM safety, but most existing studies rely solely on attack success rate (ASR) without accounting for its dependence on attack budgets, resulting in unfair comparisons across methods. Existing compute-aware evaluations reduce heterogeneous resources into FLOPs, which is difficult to estimate for black-box models and fails to capture resource-specific constraints. To provide a comparable...
-
08
When Agents Act on Web3: An Attack-Surface Survey of MCP, Skills, and Tool Calling
Rabimba Karanjai, Yang Lu, Nour Diallo, Wujie Xiong, Lei Xu, Weidong, Shi
cs.CR · cs.AI
AI agents increasingly act rather than merely read: across the Model Context Protocol (MCP) ecosystem, the share of deployed tools that modify external state has risen from 27% to 65% of tool use. When agents exercise this authority on public blockchains through MCP, skills, and tool calling, the consequences of an attack are governed by the blockchain execution layer rather than by conventional software assumptions. This survey argues that...
-
09
COMIC: Reference-Aware Safety Gating for Multimodal Large Language Models
Md Abdullahil Oaphy, Anhao Xiang, Zongxing Xie, Huayue Gu, Chenyu Wang, Honghui Xu
cs.CR · cs.AI
Multimodal large language models (MLLMs) are increasingly used to interact with screenshots, scanned documents, diagrams, and other visually grounded inputs. This shift introduces a new safety risk: in many multimodal jailbreaks, neither the prompt nor the image is harmful in isolation. Unsafe behavior emerges only when the model binds an apparently benign operation, such as summarizing, translating, or following, to a localized visual...
-
10
PACE: Policy-Attested Contract Execution for Safe AI Agents in Decentralized Finance
Rabimba Karanjai, Yang Lu, Richard Williamson, Hemanth Hm, Prakhar Mehrotra, Lei Xu, Weidong, Shi
cs.CR · cs.AI
Autonomous AI agents are emerging as interfaces for decentralized finance (DeFi) actions such as swaps, lending operations, and yield management. Because these agents rely on large language models (LLMs) to plan transactions, they inherit the LLM's susceptibility to prompt injection and lack of mechanisms to bind a verifier's approval to the exact transaction ultimately submitted on-chain. We present PACE (Policy-Attested Contract Execution),...
-
11
The Acknowledgment Point Is the System: Durable Policy-Decision Receipts for AI Audit Evidence
Neeraj Kumar Singh Beshane
cs.CR · cs.AI
An AI audit record is useful only if its durability and trust boundary are explicit. Returning a guarded decision before any durable write minimizes latency, but it cannot guarantee that evidence survives an immediate crash. We rebuild RuntimeGuard-AI around this constraint. The resulting research prototype binds each deterministic policy decision to the exact policy source, commits a privacy-minimizing record at a caller-selected...
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.