English
Related papers

Related papers: Exploiting the Index Gradients for Optimization-Ba…

200 papers

Gradient optimization-based adversarial attack methods automate the learning of adversarial triggers to generate jailbreak prompts or leak system prompts. In this work, we take a closer look at the optimization objective of adversarial…

Machine Learning · Computer Science 2025-11-21 Zhe Wang , Yanjun Qi

Large Language Models (LLMs) are often asked to generate structured outputs that obey precise syntactic rules, such as code snippets or formatted data. Grammar-constrained decoding (GCD) can guarantee that LLM outputs matches such rules by…

Computation and Language · Computer Science 2025-07-17 Kanghee Park , Timothy Zhou , Loris D'Antoni

To circumvent the alignment of large language models (LLMs), current optimization-based adversarial attacks usually craft adversarial prompts by maximizing the likelihood of a so-called affirmative response. An affirmative response is a…

Large language models (LLMs) have revolutionized lots of fields of research. Although it is well-known that fine-tuning is essential for enhancing the capabilities of LLMs, existing research suggests that there is potential redundancy in…

Artificial Intelligence · Computer Science 2025-02-14 Haoling Li , Xin Zhang , Xiao Liu , Yeyun Gong , Yifan Wang , Qi Chen , Peng Cheng

Large language models (LLMs) remain susceptible to jailbreak and direct prompt-injection attacks, yet the strongest defensive filters frequently over-refuse benign queries and degrade user experience. Previous work on jailbreak and prompt…

Computation and Language · Computer Science 2026-04-08 Purva Chiniya , Kevin Scaria , Sagar Chaturvedi

Defending large language models (LLMs) against jailbreak attacks, such as Greedy Coordinate Gradient (GCG), remains a challenge, particularly under adaptive threat models where an attacker directly targets the defense mechanism. JBShield, a…

Cryptography and Security · Computer Science 2026-05-06 Kemal Derya , Berk Sunar

Despite the remarkable performance of Large Language Models (LLMs), they remain vulnerable to jailbreak attacks, which can compromise their safety mechanisms. Existing studies often rely on brute-force optimization or manual design, failing…

Computation and Language · Computer Science 2025-06-30 Haoming Yang , Ke Ma , Xiaojun Jia , Yingfei Sun , Qianqian Xu , Qingming Huang

Retrieval Augmented Generation (RAG) frameworks improve the accuracy of large language models (LLMs) by integrating external knowledge from retrieved documents, thereby overcoming the limitations of models' static intrinsic knowledge.…

Information Retrieval · Computer Science 2025-09-19 Jingjie Zheng , Aryo Pradipta Gema , Giwon Hong , Xuanli He , Pasquale Minervini , Youcheng Sun , Qiongkai Xu

The robustness of large language models (LLMs) becomes increasingly important as their use rapidly grows in a wide range of domains. Retrieval-Augmented Generation (RAG) is considered as a means to improve the trustworthiness of text…

Computation and Language · Computer Science 2025-05-22 Zhibo Hu , Chen Wang , Yanfeng Shu , Helen , Paik , Liming Zhu

We present BadGD, a unified theoretical framework that exposes the vulnerabilities of gradient descent algorithms through strategic backdoor attacks. Backdoor attacks involve embedding malicious triggers into a training dataset to disrupt…

Machine Learning · Computer Science 2024-05-28 Chi-Hua Wang , Guang Cheng

Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level,…

Cryptography and Security · Computer Science 2025-11-25 Ryan Wong , Hosea David Yu Fei Ng , Dhananjai Sharma , Glenn Jun Jie Ng , Kavishvaran Srinivasan

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

Retrieval-Augmented Generation (RAG) systems extend large language models (LLMs) with external knowledge sources but introduce new attack surfaces through the retrieval pipeline. In particular, adversaries can poison retrieval corpora so…

Cryptography and Security · Computer Science 2026-03-20 Scott Thornton

The widespread deployment of large language models (LLMs) has raised growing concerns about their misuse risks and associated safety issues. While prior studies have examined the safety of LLMs in general usage, code generation, and…

Cryptography and Security · Computer Science 2026-01-05 Haoran Gu , Handing Wang , Yi Mei , Mengjie Zhang , Yaochu Jin

Solving arithmetic tasks is a simple and fundamental skill, yet modern Large Language Models (LLMs) have great difficulty with them. We introduce the Integrated Gated Calculator (IGC), a module that enables LLMs to perform arithmetic by…

Machine Learning · Computer Science 2025-01-03 Florian Dietz , Dietrich Klakow

Large Language Models (LLMs) are increasingly susceptible to jailbreak attacks, which are adversarial prompts that bypass alignment constraints and induce unauthorized or harmful behaviors. These vulnerabilities undermine the safety,…

Machine Learning · Computer Science 2025-09-30 Javad Forough , Mohammad Maheri , Hamed Haddadi

As the scale and complexity of jailbreaking attacks on large language models (LLMs) continue to escalate, their efficiency and practical applicability are constrained, posing a profound challenge to LLM security. Jailbreaking techniques…

Computation and Language · Computer Science 2025-12-23 Xiang Li , Chong Zhang , Jia Wang , Fangyu Wu , Yushi Li , Xiaobo Jin

In-context learning (ICL) effectively conditions large language models (LLMs) for molecular tasks, such as property prediction and molecule captioning, by embedding carefully selected demonstration examples into the input prompt. This…

Machine Learning · Computer Science 2025-02-11 Ali Al-Lawati , Jason Lucas , Zhiwei Zhang , Prasenjit Mitra , Suhang Wang

While Large Language Models (LLMs) demonstrate remarkable capabilities, they remain susceptible to sophisticated, multi-step jailbreak attacks that circumvent conventional surface-level safety alignment by exploiting the internal generation…

Machine Learning · Computer Science 2026-05-21 Jiachen Ma , Jiawen Zhang , Xiangtian Li , Bo Zou , Chaochao Lu , Chao Yang

The recent boom and rapid integration of Large Language Models (LLMs) into a wide range of applications warrants a deeper understanding of their security and safety vulnerabilities. This paper presents a comparative analysis of the…

Cryptography and Security · Computer Science 2025-11-25 Tom Perel