English
Related papers

Related papers: Circumventing Safety Alignment in Large Language M…

200 papers

Poisoning attacks can compromise the safety of large language models (LLMs) by injecting malicious documents into their training data. Existing work has studied pretraining poisoning assuming adversaries control a percentage of the training…

Large Language Models (LLMs) have demonstrated impressive capabilities in reasoning using Chain-of-Thought (CoT) prompting. However, CoT can be biased by users' instruction. In this work, we study the reasoning robustness of LLMs to…

Computation and Language · Computer Science 2024-11-11 Esther Gan , Yiran Zhao , Liying Cheng , Yancan Mao , Anirudh Goyal , Kenji Kawaguchi , Min-Yen Kan , Michael Shieh

Recent advances in large language models (LLMs) have demonstrated remarkable potential in the field of natural language processing. Unfortunately, LLMs face significant security and ethical risks. Although techniques such as safety…

Cryptography and Security · Computer Science 2025-05-27 Qingsong Zou , Jingyu Xiao , Qing Li , Zhi Yan , Yuhang Wang , Li Xu , Wenxuan Wang , Kuofeng Gao , Ruoyu Li , Yong Jiang

Mutation testing is vital for ensuring software quality. However, the presence of equivalent mutants is known to introduce redundant cost and bias issues, hindering the effectiveness of mutation testing in practical use. Although numerous…

Software Engineering · Computer Science 2024-08-06 Zhao Tian , Honglin Shu , Dong Wang , Xuejie Cao , Yasutaka Kamei , Junjie Chen

The security of Large Language Model (LLM) applications is fundamentally challenged by "form-first" attacks like prompt injection and jailbreaking, where malicious instructions are embedded within user inputs. Conventional defenses, which…

Cryptography and Security · Computer Science 2025-10-15 Dominik Schwarz

The proliferation of open-weight Large Language Models (LLMs) has democratized agentic AI, yet fine-tuned weights are frequently shared and adopted with limited scrutiny beyond leaderboard performance. This creates a risk where third-party…

Cryptography and Security · Computer Science 2026-03-05 Bhanu Pallakonda , Mikkel Hindsbo , Sina Ehsani , Prag Mishra

Despite explicit alignment efforts for large language models (LLMs), they can still be exploited to trigger unintended behaviors, a phenomenon known as "jailbreaking." Current jailbreak attack methods mainly focus on discrete prompt…

Cryptography and Security · Computer Science 2025-02-18 Guanghao Zhou , Panjia Qiu , Mingyuan Fan , Cen Chen , Mingyuan Chu , Xin Zhang , Jun Zhou

Large language models (LLMs) are known to exhibit brittle behavior under adversarial prompts and jailbreak attacks, even after extensive alignment and fine-tuning. This fragility reflects a broader challenge of modern neural language…

Computation and Language · Computer Science 2026-02-04 Patrick Cooper , Alireza Nadali , Ashutosh Trivedi , Alvaro Velasquez

Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…

Computation and Language · Computer Science 2025-06-12 Yuxin Jiang

Large Language Models (LLMs) are susceptible to malicious influence by cyber attackers through intrusions such as adversarial, backdoor, and embedding inversion attacks. In response, the burgeoning field of LLM Security aims to study and…

Computation and Language · Computer Science 2024-12-17 Yiyi Chen , Russa Biswas , Heather Lent , Johannes Bjerva

Large language models (LLMs) have demonstrated superior performance compared to previous methods on various tasks, and often serve as the foundation models for many researches and services. However, the untrustworthy third-party LLMs may…

Cryptography and Security · Computer Science 2024-04-02 Hai Huang , Zhengyu Zhao , Michael Backes , Yun Shen , Yang Zhang

Entity Alignment (EA) is vital for integrating diverse knowledge graph (KG) data, playing a crucial role in data-driven AI applications. Traditional EA methods primarily rely on comparing entity embeddings, but their effectiveness is…

Computation and Language · Computer Science 2024-10-11 Xuhui Jiang , Yinghan Shen , Zhichao Shi , Chengjin Xu , Wei Li , Zixuan Li , Jian Guo , Huawei Shen , Yuanzhuo Wang

While BERT produces high-quality sentence embeddings, its pre-training computational cost is a significant drawback. In contrast, ELECTRA provides a cost-effective pre-training objective and downstream task performance improvements, but…

Computation and Language · Computer Science 2024-10-07 Ivan Rep , David Dukić , Jan Šnajder

Aligned LLMs are secure, capable of recognizing and refusing to answer malicious questions. However, the role of internal parameters in maintaining such security is not well understood yet, further these models can be vulnerable to security…

Cryptography and Security · Computer Science 2025-04-08 Shen Li , Liuyi Yao , Lan Zhang , Yaliang Li

Jailbreak attacks pose persistent threats to large language models (LLMs). Current safety alignment methods have attempted to address these issues, but they experience two significant limitations: insufficient safety alignment depth and…

Cryptography and Security · Computer Science 2025-09-19 Yuanbo Xie , Yingjie Zhang , Tianyun Liu , Duohe Ma , Tingwen Liu

Large Language Models (LLMs) are increasingly integrated into daily routines, yet they raise significant privacy and safety concerns. Recent research proposes collaborative inference, which outsources the early-layer inference to ensure…

Cryptography and Security · Computer Science 2025-07-23 Tian Dong , Yan Meng , Shaofeng Li , Guoxing Chen , Zhen Liu , Haojin Zhu

Large language models (LLMs) are vulnerable to adversarial attacks that can elicit harmful responses. Defending against such attacks remains challenging due to the opacity of jailbreaking mechanisms and the high computational cost of…

Machine Learning · Computer Science 2025-03-21 Lei Yu , Virginie Do , Karen Hambardzumyan , Nicola Cancedda

Safety alignment is essential for the responsible deployment of large language models (LLMs). Yet, existing approaches often rely on heavyweight fine-tuning that is costly to update, audit, and maintain across model families. Full…

Cryptography and Security · Computer Science 2026-02-20 Sasha Behrouzi , Lichao Wu , Mohamadreza Rostami , Ahmad-Reza Sadeghi

Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce…

Artificial Intelligence · Computer Science 2025-05-20 Yige Li , Hanxun Huang , Yunhan Zhao , Xingjun Ma , Jun Sun

Large language models exhibit systematic vulnerabilities to adversarial attacks despite extensive safety alignment. We provide a mechanistic analysis revealing that position-dependent gradient weakening during autoregressive training…

Machine Learning · Computer Science 2025-11-18 Thong Bach , Dung Nguyen , Thao Minh Le , Truyen Tran
‹ Prev 1 8 9 10 Next ›