English
Related papers

Related papers: Cats Confuse Reasoning LLM: Query Agnostic Adversa…

200 papers

Current LLM safety research predominantly focuses on mitigating Goal Hijacking, preventing attackers from redirecting a model's high-level objective (e.g., from "summarizing emails" to "phishing users"). In this paper, we argue that this…

Cryptography and Security · Computer Science 2026-04-28 Yuansen Liu , Yixuan Tang , Anthony Kum Hoe Tun

With the boom of Large Language Models (LLMs), the research of solving Math Word Problem (MWP) has recently made great progress. However, there are few studies to examine the security of LLMs in math solving ability. Instead of attacking…

Computation and Language · Computer Science 2023-09-06 Zihao Zhou , Qiufeng Wang , Mingyu Jin , Jie Yao , Jianan Ye , Wei Liu , Wei Wang , Xiaowei Huang , Kaizhu Huang

Jailbreaks are adversarial attacks designed to bypass the built-in safety mechanisms of large language models. Automated jailbreaks typically optimize an adversarial suffix or adapt long prompt templates by forcing the model to generate the…

Computation and Language · Computer Science 2025-10-31 Raffaele Mura , Giorgio Piras , Kamilė Lukošiūtė , Maura Pintor , Amin Karbasi , Battista Biggio

The wide-ranging applications of large language models (LLMs), especially in safety-critical domains, necessitate the proper evaluation of the LLM's adversarial robustness. This paper proposes an efficient tool to audit the LLM's…

Cryptography and Security · Computer Science 2023-10-23 Xilie Xu , Keyi Kong , Ning Liu , Lizhen Cui , Di Wang , Jingfeng Zhang , Mohan Kankanhalli

Introducing reasoning models into Retrieval-Augmented Generation (RAG) systems enhances task performance through step-by-step reasoning, logical consistency, and multi-step self-verification. However, recent studies have shown that…

Cryptography and Security · Computer Science 2026-01-21 Xiaolei Zhang , Xiaojun Jia , Liquan Chen , Songze Li

The vulnerability of deep neural networks to adversarial examples has motivated an increasing number of defense strategies for promoting model robustness. However, the progress is usually hampered by insufficient robustness evaluations. As…

Machine Learning · Computer Science 2021-10-19 Xiao Yang , Yinpeng Dong , Wenzhao Xiang , Tianyu Pang , Hang Su , Jun Zhu

Detecting harmful AI actions is important as AI agents gain adoption. Chain-of-thought (CoT) monitoring is one method widely used to detect adversarial attacks and AI misalignment. However, attackers and misaligned models might evade CoT…

Computation and Language · Computer Science 2025-10-17 Shiyuan Guo , Henry Sleight , Fabien Roger

Despite the strong performance of current NLP models, they can be brittle against adversarial attacks. To enable effective learning against adversarial inputs, we introduce the use of rationale models that can explicitly learn to ignore…

Computation and Language · Computer Science 2023-02-22 Yiming Zhang , Yangqiaoyu Zhou , Samuel Carton , Chenhao Tan

Activation-based probes have emerged as a promising approach for detecting deceptively aligned AI systems by identifying internal conflict between true and stated goals. We identify a fundamental blind spot: probes fail on coherent…

Machine Learning · Computer Science 2026-03-30 Kristiyan Haralambiev

Large language models are typically trained on vast amounts of data during the pre-training phase, which may include some potentially harmful information. Fine-tuning attacks can exploit this by prompting the model to reveal such…

Cryptography and Security · Computer Science 2025-02-04 Zhiyuan Xu , Joseph Gardiner , Sana Belguith

We present LogiGAN, an unsupervised adversarial pre-training framework for improving logical reasoning abilities of language models. Upon automatic identifying logical reasoning phenomena in massive text corpus via detection heuristics, we…

Computation and Language · Computer Science 2022-12-12 Xinyu Pi , Wanjun Zhong , Yan Gao , Nan Duan , Jian-Guang Lou

Recent work has developed optimization procedures to find token sequences, called adversarial triggers, which can elicit unsafe responses from aligned language models. These triggers are believed to be highly transferable, i.e., a trigger…

Computation and Language · Computer Science 2025-04-10 Nicholas Meade , Arkil Patel , Siva Reddy

Neural networks are vulnerable to adversarial attacks -- small visually imperceptible crafted noise which when added to the input drastically changes the output. The most effective method of defending against these adversarial attacks is to…

Language models trained to solve reasoning tasks via reinforcement learning have achieved striking results. We refer to these models as reasoning models. Are the Chains of Thought (CoTs) of reasoning models more faithful than traditional…

Machine Learning · Computer Science 2025-07-16 James Chua , Owain Evans

Neural Networks (NNs) are vulnerable to adversarial examples. Such inputs differ only slightly from their benign counterparts yet provoke misclassifications of the attacked NNs. The required perturbations to craft the examples are often…

Cryptography and Security · Computer Science 2020-09-30 Philip Sperl , Konstantin Böttinger

Modern large reasoning models (LRMs) exhibit impressive multi-step problem-solving via chain-of-thought (CoT) reasoning. However, this iterative thinking mechanism introduces a new vulnerability surface. We present the Deadlock Attack, a…

Machine Learning · Computer Science 2025-10-21 Mohan Zhang , Yihua Zhang , Jinghan Jia , Zhangyang Wang , Sijia Liu , Tianlong Chen

In this paper, we tackle the emerging challenge of unintended harmful content generation in Large Language Models (LLMs) with a novel dual-stage optimisation technique using adversarial fine-tuning. Our two-pronged approach employs an…

Computation and Language · Computer Science 2023-08-29 Charles O'Neill , Jack Miller , Ioana Ciuca , Yuan-Sen Ting , Thang Bui

Natural language processing models based on neural networks are vulnerable to adversarial examples. These adversarial examples are imperceptible to human readers but can mislead models to make the wrong predictions. In a black-box setting,…

Computation and Language · Computer Science 2023-03-14 Hai Zhu , Qingyang Zhao , Yuren Wu

Machine learning models are frequently used to solve complex security problems, as well as to make decisions in sensitive situations like guiding autonomous vehicles or predicting financial market behaviors. Previous efforts have shown that…

Cryptography and Security · Computer Science 2016-04-29 Nicolas Papernot , Patrick McDaniel , Ananthram Swami , Richard Harang

Despite the success of convolutional neural networks (CNNs) in many academic benchmarks for computer vision tasks, their application in the real-world is still facing fundamental challenges. One of these open problems is the inherent lack…

Computer Vision and Pattern Recognition · Computer Science 2022-12-07 Julia Grabinski , Paul Gavrikov , Janis Keuper , Margret Keuper