English
Related papers

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

200 papers

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning and text generation. However, these models can inadvertently generate unsafe or biased responses when prompted with problematic inputs, raising…

Computation and Language · Computer Science 2024-12-03 Avinash Amballa , Durga Sandeep Saluru , Gayathri Akkinapalli , Abhishek Sureddy , Akshay Kumar Sureddy

Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in complex problem-solving through Chain-of-Thought (CoT) reasoning. However, the multi-step nature of CoT introduces new safety challenges that extend beyond…

Artificial Intelligence · Computer Science 2025-09-30 Zihao Zhu , Xinyu Wu , Gehan Hu , Siwei Lyu , Ke Xu , Baoyuan Wu

Safety alignment in large language models is remarkably shallow: it is concentrated in the first few output tokens and reversible by fine-tuning on as few as 100 adversarial examples. This fragility becomes critical in real-world…

Machine Learning · Computer Science 2026-04-21 Dongxin Guo , Jikun Wu , Siu Ming Yiu

Deep neural networks are vulnerable to adversarial examples that mislead models with imperceptible perturbations. In audio, although adversarial examples have achieved incredible attack success rates on white-box settings and black-box…

Sound · Computer Science 2022-10-13 Deng JiaCheng , Dong Li , Yan Diqun , Wang Rangding , Zeng Jiaming

Despite the increasing testing operations of automated vehicles on public roads, media reports on incidents show that safety issues caused by automated driving systems persist to this day. Manufacturers face high development uncertainty…

Systems and Control · Electrical Eng. & Systems 2025-07-08 Marvin Loba , Nayel Fabian Salem , Marcus Nolte , Andreas Dotzler , Dieter Ludwig , Markus Maurer

Large language models (LLMs), despite possessing latent safety understanding from their vast pretraining data, remain vulnerable to generating harmful content and exhibit issues such as over-refusal and utility degradation after safety…

Artificial Intelligence · Computer Science 2025-07-22 Yi Zhang , An Zhang , XiuYu Zhang , Leheng Sheng , Yuxin Chen , Zhenkai Liang , Xiang Wang

Large language model (LLM) safety classifiers such as Llama Guard are effective at detecting overtly harmful prompts but remain vulnerable to adversarial jailbreak attacks that disguise malicious intent through role-play scenarios,…

Cryptography and Security · Computer Science 2026-05-26 Lixing Lin , Juli You , Yue Li , Luyun Lin , Yiqing Wang , Zhen Zhang , Moxuan Zheng

LLMs often need effective configurations, like temperature and reasoning steps, to handle tasks requiring sophisticated reasoning and problem-solving, ranging from joke generation to mathematical reasoning. Existing prompting approaches…

Artificial Intelligence · Computer Science 2025-10-13 Xiangqi Wang , Yue Huang , Yanbo Wang , Xiaonan Luo , Kehan Guo , Yujun Zhou , Xiangliang Zhang

Safety alignment of large language models (LLMs) has been gaining increasing attention. However, current safety-aligned LLMs suffer from the fragile and imbalanced safety mechanisms, which can still be induced to generate unsafe responses,…

Computation and Language · Computer Science 2024-12-18 Weixiang Zhao , Yulin Hu , Zhuojun Li , Yang Deng , Jiahe Guo , Xingyu Sui , Yanyan Zhao , Bing Qin , Tat-Seng Chua , Ting Liu

Despite recent progress, state-of-the-art question answering models remain vulnerable to a variety of adversarial attacks. While dynamic adversarial data collection, in which a human annotator tries to write examples that fool a…

Computation and Language · Computer Science 2022-03-16 Max Bartolo , Tristan Thrush , Robin Jia , Sebastian Riedel , Pontus Stenetorp , Douwe Kiela

Recent research has shown that Large Language Models (LLMs) are vulnerable to automated jailbreak attacks, where adversarial suffixes crafted by algorithms appended to harmful queries bypass safety alignment and trigger unintended…

Computation and Language · Computer Science 2025-11-10 Chung-En Sun , Xiaodong Liu , Weiwei Yang , Tsui-Wei Weng , Hao Cheng , Aidan San , Michel Galley , Jianfeng Gao

Recent advances in large language models (LLMs) have led to increasingly sophisticated safety protocols and features designed to prevent harmful, unethical, or unauthorized outputs. However, these guardrails remain susceptible to novel and…

Computation and Language · Computer Science 2025-07-08 Annika M Schoene , Cansu Canca

Large language models can perform various reasoning tasks by using chain-of-thought prompting, which guides them to find answers through step-by-step demonstrations. However, the quality of the prompts depends on the demonstrations given to…

Computation and Language · Computer Science 2023-02-02 Zhihong Shao , Yeyun Gong , Yelong Shen , Minlie Huang , Nan Duan , Weizhu Chen

Large vision-language models (LVLMs) have achieved remarkable progress in vision-language reasoning tasks, yet ensuring their safety remains a critical challenge. Recent input-side defenses detect unsafe images with CLIP and prepend safety…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Xingyu Zhu , Beier Zhu , Junfeng Fang , Shuo Wang , Yin Zhang , Xiang Wang , Xiangnan He

When faced with novel situations, people are able to marshal relevant considerations from a wide range of background knowledge and put these to use in inferences and predictions. What permits us to draw in globally relevant information and…

Despite the remarkable capabilities of large language models, current training paradigms inadvertently foster \textit{sycophancy}, i.e., the tendency of a model to agree with or reinforce user-provided information even when it's factually…

Artificial Intelligence · Computer Science 2025-09-23 Mohammad Beigi , Ying Shen , Parshin Shojaee , Qifan Wang , Zichao Wang , Chandan Reddy , Ming Jin , Lifu Huang

Guard models are a critical component of LLM safety, but their sensitivity to superficial linguistic variations remains a key vulnerability. We show that even meaning-preserving paraphrases can cause large fluctuations in safety scores,…

Computation and Language · Computer Science 2025-11-17 Cristina Pinneri , Christos Louizos

Large Language Models have shown impressive generative capabilities across diverse tasks, but their safety remains a critical concern. Existing post-training alignment methods, such as SFT and RLHF, reduce harmful outputs yet leave LLMs…

Cryptography and Security · Computer Science 2025-10-21 Zhengyue Zhao , Yingzi Ma , Somesh Jha , Marco Pavone , Patrick McDaniel , Chaowei Xiao

Jailbreaks are adversarial attacks designed to bypass the built-in safety mechanisms of large language models. Automated jailbreaks typically optimize an adversarial suffix or adapt long prompt templates by forcing the model to generate the…

Computation and Language · Computer Science 2025-10-31 Raffaele Mura , Giorgio Piras , Kamilė Lukošiūtė , Maura Pintor , Amin Karbasi , Battista Biggio

Aligning Vision-Language Models (VLMs) with safety standards is essential to mitigate risks arising from their multimodal complexity, where integrating vision and language unveils subtle threats beyond the reach of conventional safeguards.…

Machine Learning · Computer Science 2025-10-14 Menglan Chen , Xianghe Pang , Jingjing Dong , WenHao Wang , Yaxin Du , Siheng Chen