English
Related papers

Related papers: Evaluate-and-Purify: Fortifying Code Language Mode…

200 papers

As large language models (LLMs) are becoming more capable and widespread, the study of their failure cases is becoming increasingly important. Recent advances in standardizing, measuring, and scaling test-time compute suggest new…

Machine Learning · Computer Science 2025-06-26 Mahdi Sabbaghi , Paul Kassianik , George Pappas , Yaron Singer , Amin Karbasi , Hamed Hassani

Safety aligned Large Language Models (LLMs) are vulnerable to harmful fine-tuning attacks -- a few harmful data mixed in the fine-tuning dataset can break the LLMs's safety alignment. While several defenses have been proposed, our…

Artificial Intelligence · Computer Science 2025-09-08 Tiansheng Huang , Gautam Bhattacharya , Pratik Joshi , Josh Kimball , Ling Liu

With the rapid development of Large Language Models (LLMs), their powerful code-generation capabilities have been widely applied in tasks like code completion and automated development, demonstrating the value of improving coding…

Software Engineering · Computer Science 2025-07-18 Xin Yin , Xinrui Li , Chao Ni , Xiaodan Xu , Xiaohu Yang

Large Language Models (LLMs) have recently emerged as powerful tools in cybersecurity, offering advanced capabilities in malware detection, generation, and real-time monitoring. Numerous studies have explored their application in…

Cryptography and Security · Computer Science 2025-04-11 Hamed Jelodar , Samita Bai , Parisa Hamedi , Hesamodin Mohammadian , Roozbeh Razavi-Far , Ali Ghorbani

Recent privacy research on large language models (LLMs) has shown that they achieve near-human-level performance at inferring personal data from online texts. With ever-increasing model capabilities, existing text anonymization methods are…

Artificial Intelligence · Computer Science 2025-02-04 Robin Staab , Mark Vero , Mislav Balunović , Martin Vechev

Visual language pre-training (VLP) models have demonstrated significant success across various domains, yet they remain vulnerable to adversarial attacks. Addressing these adversarial vulnerabilities is crucial for enhancing security in…

Computer Vision and Pattern Recognition · Computer Science 2025-01-22 Dehong Kong , Siyuan Liang , Xiaopeng Zhu , Yuansheng Zhong , Wenqi Ren

Recent advances in the development of large language models have resulted in public access to state-of-the-art pre-trained language models (PLMs), including Generative Pre-trained Transformer 3 (GPT-3) and Bidirectional Encoder…

Recent work shows that deep neural networks are vulnerable to adversarial examples. Much work studies adversarial example generation, while very little work focuses on more critical adversarial defense. Existing adversarial detection…

Machine Learning · Computer Science 2021-09-15 Bin Zhu , Zhaoquan Gu , Le Wang , Zhihong Tian

Although deep neural networks have achieved state-of-the-art performance in various machine learning tasks, adversarial examples, constructed by adding small non-random perturbations to correctly classified inputs, successfully fool highly…

Computation and Language · Computer Science 2022-05-02 Na Liu , Mark Dras , Wei Emma Zhang

In this work, we consider model robustness of deep neural networks against adversarial attacks from a global manifold perspective. Leveraging both the local and global latent information, we propose a novel adversarial training method…

Machine Learning · Computer Science 2022-10-04 Zhuang Qian , Shufei Zhang , Kaizhu Huang , Qiufeng Wang , Rui Zhang , Xinping Yi

Malware development and detection have undergone significant changes in recent years as modern concepts, such as machine learning, have been used for both adversarial attacks and defense. Despite intensive research on Windows Portable…

Cryptography and Security · Computer Science 2026-04-27 Lukáš Hrdonka , Martin Jureček

Software vulnerabilities, caused by unintentional flaws in source code, are a primary root cause of cyberattacks. Static analysis of source code has been widely used to detect these unintentional defects introduced by software developers.…

Software Engineering · Computer Science 2024-08-08 Andrew A Mahyari

Large language models (LLMs) undergo safety alignment to ensure safe conversations with humans. However, this paper introduces a training-free attack method capable of reversing safety alignment, converting the outcomes of stronger…

Computation and Language · Computer Science 2024-06-07 Zhanhui Zhou , Jie Liu , Zhichen Dong , Jiaheng Liu , Chao Yang , Wanli Ouyang , Yu Qiao

Given the widespread use of deep learning models in safety-critical applications, ensuring that the decisions of such models are robust against adversarial exploitation is of fundamental importance. In this thesis, we discuss recent…

Machine Learning · Computer Science 2025-09-24 Alexander Robey

Deep learning models have shown considerable vulnerability to adversarial attacks, particularly as attacker strategies become more sophisticated. While traditional adversarial training (AT) techniques offer some resilience, they often focus…

Machine Learning · Computer Science 2024-07-15 Ren Wang , Yuxuan Li , Alfred Hero

LLM-powered applications routinely embed secrets in system prompts, yet models can be tricked into revealing them. We built an adaptive attacker that evolves its strategies over hundreds of rounds and tested it against nine defense…

Cryptography and Security · Computer Science 2026-05-14 Priyal Deep , Shane Emmons , Amy Fox , Kyle Bacon , Kelley McAllister , Peter Ortiz , Krisztian Flautner

While recent works have been considerably improving the quality of the natural language explanations (NLEs) generated by a model to justify its predictions, there is very limited research in detecting and alleviating inconsistencies among…

Computation and Language · Computer Science 2023-06-06 Myeongjun Jang , Bodhisattwa Prasad Majumder , Julian McAuley , Thomas Lukasiewicz , Oana-Maria Camburu

Despite efforts to align large language models (LLMs) with human intentions, widely-used LLMs such as GPT, Llama, and Claude are susceptible to jailbreaking attacks, wherein an adversary fools a targeted LLM into generating objectionable…

Machine Learning · Computer Science 2024-06-17 Alexander Robey , Eric Wong , Hamed Hassani , George J. Pappas

Adaptive attacks have (rightfully) become the de facto standard for evaluating defenses to adversarial examples. We find, however, that typical adaptive evaluations are incomplete. We demonstrate that thirteen defenses recently published at…

Machine Learning · Computer Science 2020-10-26 Florian Tramer , Nicholas Carlini , Wieland Brendel , Aleksander Madry

The rapid adoption of open-source Large Language Models (LLMs) in offline and enterprise environments has introduced a largely unexamined security risk like susceptibility to adversarial phishing prompts under static safety configurations.…

Cryptography and Security · Computer Science 2026-04-21 Rina Mishra , Gaurav Varshney , Doddipatla Sesha Sahithi