English
Related papers

Related papers: REINFORCE Adversarial Attacks on Large Language Mo…

200 papers

Training large language models (LLMs) requires a substantial investment of time and money. To get a good return on investment, the developers spend considerable effort ensuring that the model never produces harmful and offensive outputs.…

Cryptography and Security · Computer Science 2024-07-17 Adrians Skapars , Edoardo Manino , Youcheng Sun , Lucas C. Cordeiro

Modern language models often rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors. However, they remain vulnerable to adversarial attacks due to three key limitations: (1) the inefficiency and high cost of…

Large language models (LLMs) with explicit reasoning capabilities excel at mathematical reasoning yet still commit process errors, such as incorrect calculations, brittle logic, and superficially plausible but invalid steps. In this paper,…

Artificial Intelligence · Computer Science 2026-03-26 Qihao Liu , Luoxin Ye , Wufei Ma , Yu-Cheng Chou , Alan Yuille

Retrieval-Augmented Generation (RAG) systems based on Large Language Models (LLMs) have become essential for tasks such as question answering and content generation. However, their increasing impact on public opinion and information…

Computation and Language · Computer Science 2025-12-30 Yuyang Gong , Zhuo Chen , Jiawei Liu , Miaokun Chen , Fengchang Yu , Wei Lu , Xiaofeng Wang , Xiaozhong Liu

Automatic speech recognition (ASR) systems have achieved strong performance on general transcription tasks. However, they continue to struggle with recognizing rare named entities and adapting to domain mismatches. In contrast, large…

Computation and Language · Computer Science 2025-08-21 Shaoshi Ling , Guoli Ye

State-of-the-art attacks on NLP models lack a shared definition of a what constitutes a successful attack. We distill ideas from past work into a unified framework: a successful natural language adversarial example is a perturbation that…

Computation and Language · Computer Science 2021-12-23 John X. Morris , Eli Lifland , Jack Lanchantin , Yangfeng Ji , Yanjun Qi

Safety alignment in large language models (LLMs), particularly for cybersecurity tasks, primarily focuses on preventing misuse. While this approach reduces direct harm, it obscures a complementary failure mode: denial of assistance to…

Cryptography and Security · Computer Science 2026-03-12 David Campbell , Neil Kale , Udari Madhushani Sehwag , Bert Herring , Nick Price , Dan Borges , Alex Levinson , Christina Q Knight

Motivated by the challenge to improve the adversarial robustness, security, and trust of medical decision making intelligent agents, this study develops a full-link security enhancement framework, which describes "input risk perception -…

Cryptography and Security · Computer Science 2026-05-12 Saisai Hu

Robust verbal confidence generated by large language models (LLMs) is crucial for the deployment of LLMs to help ensure transparency, trust, and safety in many applications, including those involving human-AI interactions. In this paper, we…

Computation and Language · Computer Science 2025-12-19 Stephen Obadinma , Xiaodan Zhu

Many publicly available language models have been safety tuned to reduce the likelihood of toxic or liability-inducing text. To redteam or jailbreak these models for compliance with toxic requests, users and security analysts have developed…

Computation and Language · Computer Science 2024-10-02 T. Ben Thompson , Michael Sklar

Despite the impressive adaptability of large language models (LLMs), challenges remain in ensuring their security, transparency, and interpretability. Given their susceptibility to adversarial attacks, LLMs need to be defended with an…

Artificial Intelligence · Computer Science 2024-10-11 Tomas Bueno Momcilovic , Beat Buesser , Giulio Zizzo , Mark Purcell , Dian Balta

Pre-trained language models (PLMs) have driven substantial progress in natural language processing but remain vulnerable to adversarial attacks, raising concerns about their robustness in real-world applications. Previous studies have…

Computation and Language · Computer Science 2025-10-17 Yang Wang , Chenghao Xiao , Yizhi Li , Stuart E. Middleton , Noura Al Moubayed , Chenghua Lin

Large language models (LLMs) are popular for high-quality text generation but can produce harmful content, even when aligned with human values through reinforcement learning. Adversarial prompts can bypass their safety measures. We propose…

Computation and Language · Computer Science 2024-05-03 Mansi Phute , Alec Helbling , Matthew Hull , ShengYun Peng , Sebastian Szyller , Cory Cornelius , Duen Horng Chau

Large language models (LLMs) remain vulnerable to adversarial prompting despite advances in alignment and safety, often exhibiting harmful behaviors under novel attack strategies. While adversarial training can improve robustness, existing…

Machine Learning · Computer Science 2026-05-08 Yiwei Zhang , Jeremiah Birrell , Reza Ebrahimi , Rouzbeh Behnia , Jason Pacheco , Elisa Bertino

The surge of state-of-the-art Transformer-based models has undoubtedly pushed the limits of NLP model performance, excelling in a variety of tasks. We cast the spotlight on the underexplored task of Natural Language Inference (NLI), since…

Computation and Language · Computer Science 2025-08-04 Alexandros Koulakos , Maria Lymperaiou , Giorgos Filandrianos , Giorgos Stamou

Adversarial attacks can reliably steer safety-aligned large language models toward unsafe behavior. Empirically, we find that adversarial prompt-injection attacks can amplify attack success rate from the slow polynomial growth observed…

Machine Learning · Computer Science 2026-05-29 Indranil Halder , Annesya Banerjee , Cengiz Pehlevan

Applications that use Large Language Models (LLMs) are becoming widespread, making the identification of system vulnerabilities increasingly important. Automated Red Teaming accelerates this effort by using an LLM to generate and execute…

Jailbreak attacks against large language models (LLMs) aim to induce harmful behaviors in LLMs through carefully crafted adversarial prompts. To mitigate attacks, one way is to perform adversarial training (AT)-based alignment, i.e.,…

Machine Learning · Computer Science 2026-02-03 Shaopeng Fu , Liang Ding , Jingfeng Zhang , Di Wang

In the rapidly evolving field of machine learning, adversarial attacks present a significant challenge to model robustness and security. Decision-based attacks, which only require feedback on the decision of a model rather than detailed…

Cryptography and Security · Computer Science 2024-05-24 Ping Guo , Fei Liu , Xi Lin , Qingchuan Zhao , Qingfu Zhang

Jailbreak vulnerabilities in Large Language Models (LLMs) refer to methods that extract malicious content from the model by carefully crafting prompts or suffixes, which has garnered significant attention from the research community.…

Cryptography and Security · Computer Science 2024-09-13 Lijia Lv , Weigang Zhang , Xuehai Tang , Jie Wen , Feng Liu , Jizhong Han , Songlin Hu