English
Related papers

Related papers: Differentiated Directional Intervention A Framewor…

200 papers

Defending large language models (LLMs) against jailbreak attacks is essential for their safe and reliable deployment. Existing defenses often rely on shallow pattern matching, which struggles to generalize to novel and unseen attack…

Artificial Intelligence · Computer Science 2025-08-06 Rui Pu , Chaozhuo Li , Rui Ha , Litian Zhang , Lirong Qiu , Xi Zhang

Safety alignment in large language models (LLMs) and multimodal large language models (MLLMs) is commonly assumed to operate as a near-binary threshold mechanism. We challenge this assumption by revealing that safety behavior is governed by…

Cryptography and Security · Computer Science 2026-05-27 Tongxi Wu , Jian Zhang , Yang Gao

The deployment of Large Language Models (LLMs) in diverse applications necessitates an assurance of safety without compromising the contextual integrity of the generated content. Traditional approaches, including safety-specific fine-tuning…

Computation and Language · Computer Science 2024-07-01 Shaina Raza , Ananya Raval , Veronica Chatrath

Generalizable alignment is a core challenge for deploying Large Language Models (LLMs) safely in real-world NLP applications. Current alignment methods, including Reinforcement Learning from Human Feedback (RLHF), often fail to guarantee…

Computation and Language · Computer Science 2025-04-07 Jaymari Chua , Chen Wang , Lina Yao

Large Language Models (LLMs) fine-tuned to align with human values often exhibit alignment drift, producing unsafe or policy-violating completions when exposed to adversarial prompts, decoding perturbations, or paraphrased jailbreaks. While…

Artificial Intelligence · Computer Science 2025-08-05 Amitava Das , Vinija Jain , Aman Chadha

While large language models (LLMs) exhibit remarkable capabilities across various tasks, they encounter potential security risks such as jailbreak attacks, which exploit vulnerabilities to bypass security measures and generate harmful…

Cryptography and Security · Computer Science 2024-11-28 Xinyuan Wang , Victor Shea-Jay Huang , Renmiao Chen , Hao Wang , Chengwei Pan , Lei Sha , Minlie Huang

Safety alignment in Large Language Models (LLMs) often creates a systematic discrepancy between a model's aligned output and the underlying pre-aligned data distribution. We propose a framework in which the effect of safety alignment on…

Computation and Language · Computer Science 2026-02-03 Yuxuan Lu , Yongkang Guo , Yuqing Kong

Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have improved the safety of large language models (LLMs). However,…

Computation and Language · Computer Science 2026-02-26 Mengxuan Hu , Vivek V. Datla , Anoop Kumar , Zihan Guan , Sheng Li , Alfy Samuel , Daben Liu

Recent work has shown that language models' refusal behavior is primarily encoded in a single direction in their latent space, making it vulnerable to targeted attacks. Although Latent Adversarial Training (LAT) attempts to improve…

Computation and Language · Computer Science 2025-04-29 Alexandra Abbas , Nora Petrova , Helios Ael Lyons , Natalia Perez-Campanero

Large language models (LLMs) have demonstrated impressive performance and have come to dominate the field of natural language processing (NLP) across various tasks. However, due to their strong instruction-following capabilities and…

Cryptography and Security · Computer Science 2026-04-10 Yulin Chen , Haoran Li , Yuan Sui , Yue Liu , Yufei He , Xiaoling Bai , Chi Fei , Yabo Li , Haozhe Ma , Yangqiu Song , Bryan Hooi

Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they remain vulnerable to adversarial manipulations such as jailbreaking via prompt injection attacks. These attacks bypass safety mechanisms…

Machine Learning · Computer Science 2025-07-08 Xin Wei Chia , Swee Liang Wong , Jonathan Pan

Direct Prompt Injection (DPI) attacks pose a critical security threat to Large Language Models (LLMs) due to their low barrier of execution and high potential damage. To address the impracticality of existing white-box/gray-box methods and…

Artificial Intelligence · Computer Science 2025-09-10 Minghui Li , Hao Zhang , Yechao Zhang , Wei Wan , Shengshan Hu , pei Xiaobing , Jing Wang

This work introduces a novel framework for evaluating LLMs' capacity to balance instruction-following with critical reasoning when presented with multiple-choice questions containing no valid answers. Through systematic evaluation across…

Computation and Language · Computer Science 2025-06-03 Gracjan Góral , Emilia Wiśnios , Piotr Sankowski , Paweł Budzianowski

Modern large language model (LLM) developers typically conduct a safety alignment to prevent an LLM from generating unethical or harmful content. Recent studies have discovered that the safety alignment of LLMs can be bypassed by…

Cryptography and Security · Computer Science 2024-06-14 Xuan Chen , Yuzhou Nie , Lu Yan , Yunshu Mao , Wenbo Guo , Xiangyu Zhang

With the increasing adoption of Large Language Models (LLMs), more customization is needed to ensure privacy-preserving and safe generation. We address this objective from two critical aspects: unlearning of sensitive information and…

Machine Learning · Computer Science 2025-10-17 Fatmazohra Rezkellah , Ramzi Dakhmouche

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We…

Machine Learning · Computer Science 2025-06-23 Tianle Gu , Kexin Huang , Zongqi Wang , Yixu Wang , Jie Li , Yuanqi Yao , Yang Yao , Yujiu Yang , Yan Teng , Yingchun Wang

Safety, security, and compliance are essential requirements when aligning large language models (LLMs). However, many seemingly aligned LLMs are soon shown to be susceptible to jailbreak attacks. These attacks aim to circumvent the models'…

Cryptography and Security · Computer Science 2025-06-05 Chen Xiong , Xiangyu Qi , Pin-Yu Chen , Tsung-Yi Ho

As Large Language Models quickly become ubiquitous, it becomes critical to understand their security vulnerabilities. Recent work shows that text optimizers can produce jailbreaking prompts that bypass moderation and alignment. Drawing from…

Drug-drug interaction (DDI) prediction is critical for treatment safety. While large language models (LLMs) show promise in pharmaceutical tasks, their effectiveness in DDI prediction remains challenging. Inspired by the well-established…

Artificial Intelligence · Computer Science 2025-05-30 Guangyi Liu , Yongqi Zhang , Xunyuan Liu , Quanming Yao

Safety alignment in Large Language Models (LLMs) remains highly fragile during fine-tuning, where even benign adaptation can degrade pre-trained refusal behaviors and enable harmful responses. Existing defenses typically constrain either…

Artificial Intelligence · Computer Science 2026-04-15 Songping Peng , Zhiheng Zhang , Daojian Zeng , Lincheng Jiang , Xieping Gao