The paper introduces a privacy‑preserving zk‑SNARK audit framework that uses adversarial‑style probes to detect logit drift between an approved large language model and a modified deployment. It offers three probe families—token‑based (black‑box), embedding‑based (gray‑box), and stress probes (partial white‑box)—allowing users to balance sensitivity, access, and cost. Experiments across LLM architectures and GPU platforms show token‑based probes achieve the highest mean sensitivity while remaining practical in a black‑box setting, with Groth16 proving times scaling modestly from 1.02 to 1.78 seconds and constant proof size.
By Cameron Wilding, Mina Shaker, Fatemeh Ganji
arXiv:2607. 00481v1 Announce Type: cross Abstract: Jailbreak attacks remain a critical threat to the safe deployment of large language models (LLMs).
By Junlong Liu, Haobo Wang, Weiqi Luo, Xiaojun Jia
The paper introduces AdvGuard, a model‑agnostic framework designed to detect and mitigate query‑based system prompt leakage attacks against large language models. AdvGuard constructs a bounded semantic interaction graph to capture cross‑query relationships, applies statistical filtering, and uses graph convolutional networks for classification, enabling it to identify coordinated extraction attempts across multiple turns. In evaluations, AdvGuard achieves significant improvements in recall and F1 scores over baselines, with negligible false positives, and effectively limits prompt leakage in adaptive attack scenarios.
By Tushar Nayan, Pratik Poudel, Qian Lou, Yuede Ji, Jason Liu, Ruimin Sun
Reflex-Guard is a lightweight, locally‑run guardrail for large language models that uses jailbreak‑aware preprocessing, compact sentence‑transformer embeddings, and seven fast binary classifiers to filter unsafe prompts. It achieves 95.9 % recall on harmful prompts with an end‑to‑end latency of 37.6 ms, outperforming existing solutions such as Llama Guard 2 (255 ms) and SafeDecoding (723 ms). The system can detect all GCG suffix attacks and Base64‑encoded prompts at the default threshold, while DrAttack structured prompts require a lower threshold of 0.03 for optimal detection, and it attains a Reflex Efficiency Score of up to 16.79.
By Istiaque Ahmed, Afia Anjum Borsha, Ranat Das Prangon, Abu-fuad Ahmad, Thi Hong Tran
arXiv:2605. 01143v2 Announce Type: replace Abstract: Large Language Model (LLM)-powered agents demonstrate strong capabilities in autonomous task execution, tool use, and multi-step reasoning.
By Sheldon Yu, Yingcheng Sun, Hanqing Guo, Qianqian Tong
Reflex-Guard is a lightweight, locally running guardrail for large language models that uses jailbreak-aware preprocessing, compact sentence‑transformer embeddings, and seven fast binary classifiers to filter unsafe prompts. It achieves 95.9% recall on harmful prompts with an end‑to‑end latency of 37.6 ms, far faster than existing solutions such as Llama Guard 2 (255 ms) and SafeDecoding (723 ms). The system can detect all GCG suffix attacks and Base64‑encoded prompts at the default threshold, and it attains a Reflex Efficiency Score up to 16.79, outperforming its competitors.
arXiv:2606. 19262v1 Announce Type: new Abstract: Hardware-enabled monitoring of GPU workloads underpins many proposals for AI compute governance, but if developers can defeat monitoring mechanisms, such schemes are unworkable.
By Robi Rahman, Sabiha Tajdari
The paper introduces a unified framework for monitoring misuse of large language model agents in multi‑actor settings, focusing on two attack types: decomposition attacks and prompt injection attacks. It proposes tracking the agent’s externalised actions and determining whether the first detection of harm falls within a defined harm window. Using this formalism, the authors build a benchmark of about 6,200 conversation transcripts and evaluate 17 monitor configurations, finding that action‑framed monitors perform well on both threats while content‑framed monitors struggle with injection attacks, and highlighting limitations of traditional position‑blind metrics.
By Aniruddh Pramod, James Oldfield, Adel Bibi
arXiv:2604. 07223v2 Announce Type: replace-cross Abstract: As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to intermediate execution traces.
By Yen-Shan Chen, Sian-Yao Huang, Cheng-Lin Yang, Yun-Nung Chen
The paper introduces CUAHarm, a benchmark comprising 104 expert‑written realistic misuse scenarios for computer‑using agents (CUAs), such as disabling firewalls or leaking data. Using a sandbox with verifiable rewards, the authors evaluate frontier language models—including GPT‑5, Claude 4 Sonnet, Gemini 2.5 Pro, Llama‑3.3‑70B, and Mistral Large 2—and find that even without jailbreak prompts, these models can successfully execute many malicious tasks at high rates (e.g., 90% for Gemini 2.5 Pro). The study also shows that newer models, while safer in traditional safety benchmarks, exhibit higher misuse risks as CUAs, and that monitoring CUAs’ actions remains challenging, with current methods achieving only about 77% accuracy.
By Aaron Xuxiang Tian, Ruofan Zhang, Janet Tang, Ji Wang, Tianyu Shi, Jiaxin Wen
arXiv:2609.36879v1 Announce Type: cross
Abstract: As LLM-based agents perform increasingly complex tasks, Agent Skills have emerged as a flexible mechanism for extending their capabilities. An Agent...
By Haoran Ou, Gelei Deng, Xuanye Zhang, Wenbo Guo, Tianwei Zhang, Kwok-Yan Lam
arXiv:2609.31877v2 Announce Type: replace-cross
Abstract: Cloud-based Large language model (LLM) services create a network-level traffic side channel that can expose model, prompt, and task behavior...
By Shahrooz Pouryousef, Jesus Lopez, Saeefa Rubaiyet Nowmi, Md Mahmuduzzaman Kamol, Moinul Hossain, Muoi Tran, Mohammad Saidur Rahman