English
Related papers

Related papers: Self-Guided Defense: Adaptive Safety Alignment for…

200 papers

Large Language Models (LLMs) have enabled the development of powerful agentic systems capable of automating complex workflows across various fields. However, these systems are highly vulnerable to indirect prompt injection attacks, where…

Cryptography and Security · Computer Science 2026-01-16 Hao Li , Yankai Yang , G. Edward Suh , Ning Zhang , Chaowei Xiao

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

Recursive self-improvement--where a model iteratively trains on its own outputs--promises sustained capability growth but faces a fundamental obstacle: recursive drift. As models train on self-generated data across multiple iterations,…

Artificial Intelligence · Computer Science 2026-03-24 Xinyu Zhang

Large Language Models (LLMs) exhibit impressive capabilities but also present risks such as biased content generation and privacy issues. One of the current alignment techniques includes principle-driven integration, but it faces challenges…

Computation and Language · Computer Science 2025-05-30 Yi Luo , Zhenghao Lin , Yuhao Zhang , Jiashuo Sun , Chen Lin , Chengjin Xu , Xiangdong Su , Yelong Shen , Jian Guo , Yeyun Gong

The deployment of large language models (LLMs) has raised security concerns due to their susceptibility to producing harmful or policy-violating outputs when exposed to adversarial prompts. While alignment and guardrails mitigate common…

Computation and Language · Computer Science 2026-01-23 Rishit Chugh

Recent reasoning-based safety guardrails for Large Reasoning Models (LRMs), such as deliberative alignment, have shown strong defense against jailbreak attacks. By leveraging LRMs' reasoning ability, these guardrails help the models to…

Cryptography and Security · Computer Science 2025-10-24 Shuo Chen , Zhen Han , Haokun Chen , Bailan He , Shengyun Si , Jingpei Wu , Philip Torr , Volker Tresp , Jindong Gu

Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…

Machine Learning · Computer Science 2024-08-22 Samyak Jain , Ekdeep Singh Lubana , Kemal Oksuz , Tom Joy , Philip H. S. Torr , Amartya Sanyal , Puneet K. Dokania

Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also amplifies potential risks such as jailbreak attacks that circumvent built-in safety mechanisms.…

Artificial Intelligence · Computer Science 2025-10-01 Qinjian Zhao , Jiaqi Wang , Zhiqiang Gao , Zhihao Dou , Belal Abuhaija , Kaizhu Huang

Multimodal large language models (MLLMs) have demonstrated impressive reasoning and instruction-following capabilities, yet their expanded modality space introduces new compositional safety risks that emerge from complex text-image…

Cryptography and Security · Computer Science 2025-11-18 Xuankun Rong , Wenke Huang , Tingfeng Wang , Daiguo Zhou , Bo Du , Mang Ye

Large reasoning models (LRMs) achieve remarkable performance by leveraging reinforcement learning (RL) on reasoning tasks to generate long chain-of-thought (CoT) reasoning. However, this over-optimization often prioritizes compliance,…

Artificial Intelligence · Computer Science 2026-05-14 Seanie Lee , Sangwoo Park , Yumin Choi , Gyeongman Kim , Minki Kang , Jihun Yun , Dongmin Park , Jongho Park , Sung Ju Hwang

A major challenge to deploying cyber-physical systems with learning-enabled controllers is to ensure their safety, especially in the face of changing environments that necessitate runtime knowledge acquisition. Model-checking and automated…

Programming Languages · Computer Science 2025-02-27 Yao Feng , Jun Zhu , André Platzer , Jonathan Laurent

Text-to-image diffusion models have revolutionized visual content generation, yet their deployment is hindered by a fundamental limitation: safety mechanisms enforce rigid, uniform standards that fail to reflect diverse user preferences…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Yu Lei , Jinbin Bai , Qingyu Shi , Aosong Feng , Hongcheng Gao , Xiao Zhang , Rex Ying

The current paradigm for safety alignment of large language models (LLMs) follows a one-size-fits-all approach: the model refuses to interact with any content deemed unsafe by the model provider. This approach lacks flexibility in the face…

Computation and Language · Computer Science 2025-03-05 Jingyu Zhang , Ahmed Elgohary , Ahmed Magooda , Daniel Khashabi , Benjamin Van Durme

Offline reinforcement learning (RL) agents often fail when deployed, as the gap between training datasets and real environments leads to unsafe behavior. To address this, we present SAS (Self-Alignment for Safety), a transformer-based…

Machine Learning · Computer Science 2026-04-30 Seungyub Han , Hyungjin Kim , Jungwoo Lee

Although safely enhanced Large Language Models (LLMs) have achieved remarkable success in tackling various complex tasks in a zero-shot manner, they remain susceptible to jailbreak attacks, particularly the unknown jailbreak attack. To…

Computation and Language · Computer Science 2024-06-12 Fan Liu , Zhao Xu , Hao Liu

The emergence of autonomous Large Language Model (LLM) agents capable of tool usage has introduced new safety risks that go beyond traditional conversational misuse. These agents, empowered to execute external functions, are vulnerable to…

Artificial Intelligence · Computer Science 2025-07-14 Zeyang Sha , Hanling Tian , Zhuoer Xu , Shiwen Cui , Changhua Meng , Weiqiang Wang

Aspect-based Sentiment Analysis (ABSA) is a sentiment analysis task at fine-grained level. Recently, generative frameworks have attracted increasing attention in ABSA due to their ability to unify subtasks and their continuity to upstream…

Computation and Language · Computer Science 2023-02-28 Chengze Yu , Taiqiang Wu , Jiayi Li , Xingyu Bai , Yujiu Yang

Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment, which often relies on rigid refusal heuristics or representation engineering to block harmful outputs. While they are…

Computation and Language · Computer Science 2025-10-01 Yuyou Zhang , Miao Li , William Han , Yihang Yao , Zhepeng Cen , Ding Zhao

Large Language Models (LLMs) are increasingly attracting attention in various applications. Nonetheless, there is a growing concern as some users attempt to exploit these models for malicious purposes, including the synthesis of controlled…

Artificial Intelligence · Computer Science 2025-08-26 Chongwen Zhao , Zhihao Dou , Kaizhu Huang

LLMs have made impressive progress, but their growing capabilities also expose them to highly flexible jailbreaking attacks designed to bypass safety alignment. While many existing defenses focus on known types of attacks, it is more…

Cryptography and Security · Computer Science 2025-05-27 Haoyu Wang , Zeyu Qin , Yifei Zhao , Chao Du , Min Lin , Xueqian Wang , Tianyu Pang