English
Related papers

Related papers: Fast Proxies for LLM Robustness Evaluation

200 papers

Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails. In many domains, adversarial training has proven to be one of the most promising methods to reliably improve robustness against such…

Machine Learning · Computer Science 2024-11-04 Sophie Xhonneux , Alessandro Sordoni , Stephan Günnemann , Gauthier Gidel , Leo Schwinn

Process Reward Models (PRMs) are rapidly becoming the backbone of LLM reasoning pipelines, yet we demonstrate that state-of-the-art PRMs are systematically exploitable under adversarial optimization pressure. To address this, we introduce a…

Most discussions about Large Language Model (LLM) safety have focused on single-agent settings but multi-agent LLM systems now create novel adversarial risks because their behavior depends on communication between agents and decentralized…

Multiagent Systems · Computer Science 2025-10-10 Rana Muhammad Shahroz Khan , Zhen Tan , Sukwon Yun , Charles Fleming , Tianlong Chen

Multi-tenant LLM serving frameworks widely adopt shared Key-Value caches to enhance efficiency. However, this creates side-channel vulnerabilities enabling prompt leakage attacks. Prior studies identified these attack surfaces yet focused…

Cryptography and Security · Computer Science 2026-02-25 Longxiang Wang , Xiang Zheng , Xuhao Zhang , Yao Zhang , Ye Wu , Cong Wang

In large-scale industrial LLM systems, prompt templates often expand to thousands of tokens as teams iteratively incorporate sections such as task instructions, few-shot examples, and heuristic rules to enhance robustness and coverage. This…

Computation and Language · Computer Science 2025-10-09 Zhentao Xu , Fengyi Li , Albert Chen , Xiaofeng Wang

As large language models are integrated into society, robustness toward a suite of prompts is increasingly important to maintain reliability in a high-variance environment.Robustness evaluations must comprehensively encapsulate the various…

Computation and Language · Computer Science 2023-11-14 Alex Mei , Sharon Levy , William Yang Wang

System prompts have emerged as a critical control surface for specifying the behavior of LLMs in chat and agent settings. Developers depend on system prompts to specify important context, output format, personalities, guardrails, content…

Computation and Language · Computer Science 2025-02-19 Norman Mu , Jonathan Lu , Michael Lavery , David Wagner

As Large Language Models (LLMs) increasingly become key components in various AI applications, understanding their security vulnerabilities and the effectiveness of defense mechanisms is crucial. This survey examines the security challenges…

Machine Learning · Computer Science 2024-06-04 Frank Weizhen Liu , Chenhui Hu

This work aims to investigate how different Large Language Models (LLMs) alignment methods affect the models' responses to prompt attacks. We selected open source models based on the most common alignment methods, namely, Supervised…

Recently, it has been widely known that deep neural networks are highly vulnerable and easily broken by adversarial attacks. To mitigate the adversarial vulnerability, many defense algorithms have been proposed. Recently, to improve…

Computer Vision and Pattern Recognition · Computer Science 2023-06-28 Hong Joo Lee , Yong Man Ro

Language models have become increasingly powerful tools for formal mathematical reasoning. However, most existing approaches rely exclusively on either large general-purpose models or smaller specialized models, each with distinct…

Artificial Intelligence · Computer Science 2025-07-22 Nicolas Wischermann , Claudio Mayrink Verdun , Gabriel Poesia , Francesco Noseda

Large Reasoning Models (LRMs) have demonstrated remarkable performance on tasks such as mathematics and code generation. Motivated by these strengths, recent work has empirically demonstrated the effectiveness of LRMs as guard models in…

Cryptography and Security · Computer Science 2025-09-29 Jiawei Zhao , Yuang Qi , Weiming Zhang , Nenghai Yu , Kejiang Chen

Legged locomotion has recently achieved remarkable success with the progress of machine learning techniques, especially deep reinforcement learning (RL). Controllers employing neural networks have demonstrated empirical and qualitative…

Robotics · Computer Science 2024-06-03 Fan Shi , Chong Zhang , Takahiro Miki , Joonho Lee , Marco Hutter , Stelian Coros

Web-browsing AI agents are increasingly deployed in enterprise settings under strict whitelists of approved domains, yet adversaries can still influence them by embedding hidden instructions in the HTML pages those domains serve. Existing…

Cryptography and Security · Computer Science 2026-05-13 Chia-Pei , Chen , Kentaroh Toyoda , Anita Lai , Alex Leung

LLM-integrated applications and agents are vulnerable to prompt injection attacks, where adversaries embed malicious instructions within seemingly benign input data to manipulate the LLM's intended behavior. Recent defenses based on…

Cryptography and Security · Computer Science 2025-12-09 Sarthak Choudhary , Divyam Anshumaan , Nils Palumbo , Somesh Jha

The increasing deployment of Large Language Models (LLMs) in various applications necessitates a rigorous evaluation of their robustness against adversarial attacks. In this paper, we present a comprehensive study on the robustness of GPT…

Computation and Language · Computer Science 2024-12-24 Yiyi Tao , Yixian Shen , Hang Zhang , Yanxin Shen , Lun Wang , Chuanqi Shi , Shaoshuai Du

Prompt injection attacks pose a pervasive threat to the security of Large Language Models (LLMs). State-of-the-art prevention-based defenses typically rely on fine-tuning an LLM to enhance its security, but they achieve limited…

Cryptography and Security · Computer Science 2025-11-17 Yupei Liu , Yanting Wang , Yuqi Jia , Jinyuan Jia , Neil Zhenqiang Gong

As powerful Large Language Models (LLMs) are now widely used for numerous practical applications, their safety is of critical importance. While alignment techniques have significantly improved overall safety, LLMs remain vulnerable to…

Machine Learning · Computer Science 2024-10-28 Samuel Jacob Chacko , Sajib Biswas , Chashi Mahiul Islam , Fatema Tabassum Liza , Xiuwen Liu

The proliferation of Large Language Models (LLMs) has introduced critical security challenges, where adversarial actors can manipulate input prompts to cause significant harm and circumvent safety alignments. These prompt-based attacks…

Recent years have seen the wide application of NLP models in crucial areas such as finance, medical treatment, and news media, raising concerns of the model robustness and vulnerabilities. In this paper, we propose a novel prompt-based…

Computation and Language · Computer Science 2022-03-22 Yuting Yang , Pei Huang , Juan Cao , Jintao Li , Yun Lin , Jin Song Dong , Feifei Ma , Jian Zhang