English
Related papers

Related papers: Logically Consistent Adversarial Attacks for Soft …

200 papers

Recent studies show that pre-trained language models (LMs) are vulnerable to textual adversarial attacks. However, existing attack methods either suffer from low attack success rates or fail to search efficiently in the exponentially large…

Computation and Language · Computer Science 2022-06-14 Boxin Wang , Chejian Xu , Xiangyu Liu , Yu Cheng , Bo Li

Most adversarial threats in artificial intelligence (AI) target the computational behavior of models rather than the humans who rely on them. Yet modern AI systems increasingly operate within human decision loops, where users interpret and…

Artificial Intelligence · Computer Science 2026-05-18 Shutong Fan , Lan Zhang , Xiaoyong Yuan

Large language models (LLMs) achieve strong performance across many tasks but remain vulnerable to hallucinations, motivating the need for realistic adversarial prompts that elicit such failures. We formulate hallucination elicitation as a…

Computation and Language · Computer Science 2026-05-14 Buyun Liang , Jinqi Luo , Liangzu Peng , Kwan Ho Ryan Chan , Darshan Thaker , Kaleab A. Kinfu , Fengrui Tian , Hamed Hassani , René Vidal

Over the past decade, there has been extensive research aimed at enhancing the robustness of neural networks, yet this problem remains vastly unsolved. Here, one major impediment has been the overestimation of the robustness of new defense…

Artificial Intelligence · Computer Science 2023-10-31 Leo Schwinn , David Dobre , Stephan Günnemann , Gauthier Gidel

The increasing capabilities of Large Language Models (LLMs) have raised concerns about their misuse in AI-generated plagiarism and social engineering. While various AI-generated text detectors have been proposed to mitigate these risks,…

Computation and Language · Computer Science 2025-10-31 Yize Cheng , Vinu Sankar Sadasivan , Mehrdad Saberi , Shoumik Saha , Soheil Feizi

Deep learning models, while achieving state-of-the-art performance on many tasks, are susceptible to adversarial attacks that exploit inherent vulnerabilities in their architectures. Adversarial attacks manipulate the input data with…

Computer Vision and Pattern Recognition · Computer Science 2023-12-07 Shreyasi Mandal

This paper presents an approach to developing assurance cases for adversarial robustness and regulatory compliance in large language models (LLMs). Focusing on both natural and code language tasks, we explore the vulnerabilities these…

Cryptography and Security · Computer Science 2024-10-10 Tomas Bueno Momcilovic , Dian Balta , Beat Buesser , Giulio Zizzo , Mark Purcell

Large Language Models (LLMs) are valuable for text classification, but their vulnerabilities must not be disregarded. They lack robustness against adversarial examples, so it is pertinent to understand the impacts of different types of…

Computation and Language · Computer Science 2024-06-13 João Vitorino , Eva Maia , Isabel Praça

Adversarial training for neural networks has been in the limelight in recent years. The advancement in neural network architectures over the last decade has led to significant improvement in their performance. It sparked an interest in…

Machine Learning · Computer Science 2022-06-07 Abhijith Sharma , Apurva Narayan

Convolutional neural networks have been used to achieve a string of successes during recent years, but their lack of interpretability remains a serious issue. Adversarial examples are designed to deliberately fool neural networks into…

Machine Learning · Computer Science 2020-04-28 Jan Philip Göpfert , André Artelt , Heiko Wersing , Barbara Hammer

Because "out-of-the-box" large language models are capable of generating a great deal of objectionable content, recent work has focused on aligning these models in an attempt to prevent undesirable generation. While there has been some…

Computation and Language · Computer Science 2023-12-22 Andy Zou , Zifan Wang , Nicholas Carlini , Milad Nasr , J. Zico Kolter , Matt Fredrikson

We investigate the robustness of reasoning models trained for step-by-step problem solving by introducing query-agnostic adversarial triggers - short, irrelevant text that, when appended to math problems, systematically mislead models to…

Recent studies reveal that Convolutional Neural Networks (CNNs) are typically vulnerable to adversarial attacks, which pose a threat to security-sensitive applications. Many adversarial defense methods improve robustness at the cost of…

Computer Vision and Pattern Recognition · Computer Science 2021-06-17 Tao Wang , Ruixin Zhang , Xingyu Chen , Kai Zhao , Xiaolin Huang , Yuge Huang , Shaoxin Li , Jilin Li , Feiyue Huang

With the development of large language models (LLMs), detecting whether text is generated by a machine becomes increasingly challenging in the face of malicious use cases like the spread of false information, protection of intellectual…

Computation and Language · Computer Science 2024-04-03 Ying Zhou , Ben He , Le Sun

Recent advancements in natural language processing have highlighted the vulnerability of deep learning models to adversarial attacks. While various defence mechanisms have been proposed, there is a lack of comprehensive benchmarks that…

Computation and Language · Computer Science 2025-01-23 Yang Wang , Chenghua Lin

As the deployment of NLP systems in critical applications grows, ensuring the robustness of large language models (LLMs) against adversarial attacks becomes increasingly important. Large language models excel in various NLP tasks but remain…

Computation and Language · Computer Science 2024-05-03 Zhenning Yang , Ryan Krawec , Liang-Yuan Wu

State-of-art deep neural networks (DNN) are vulnerable to attacks by adversarial examples: a carefully designed small perturbation to the input, that is imperceptible to human, can mislead DNN. To understand the root cause of adversarial…

Machine Learning · Statistics 2019-10-29 Xupeng Shi , A. Adam Ding

The rapid evolution of Text-to-Video (T2V) diffusion models has driven remarkable advancements in generating high-quality, temporally coherent videos from natural language descriptions. Despite these achievements, their vulnerability to…

Computer Vision and Pattern Recognition · Computer Science 2026-01-01 Changzhen Li , Yuecong Min , Jie Zhang , Zheng Yuan , Shiguang Shan , Xilin Chen

Adversarial factuality refers to the deliberate insertion of misinformation into input prompts by an adversary, characterized by varying levels of expressed confidence. In this study, we systematically evaluate the performance of several…

Computation and Language · Computer Science 2025-03-17 Shahnewaz Karim Sakib , Anindya Bijoy Das , Shibbir Ahmed

Upon the discovery of adversarial attacks, robust models have become obligatory for deep learning-based systems. Adversarial training with first-order attacks has been one of the most effective defenses against adversarial perturbations to…

Computer Vision and Pattern Recognition · Computer Science 2021-08-24 Inci M. Baytas , Debayan Deb