English
Related papers

Related papers: Gradient-Controlled Decoding: A Safety Guardrail f…

200 papers

Despite extensive alignment efforts, Large Vision-Language Models (LVLMs) remain vulnerable to jailbreak attacks. To mitigate these risks, existing detection methods are essential, yet they face two major challenges: generalization and…

Cryptography and Security · Computer Science 2026-01-28 Shuang Liang , Zhihao Xu , Jiaqi Weng , Jialing Tao , Hui Xue , Xiting Wang

Backdoor attacks poison the training data, causing the model to behave normally on clean inputs but predict attacker-chosen labels when trigger patterns are embedded into the input samples. Defending against such attacks is highly…

Cryptography and Security · Computer Science 2026-04-28 Wei Guo , Maura Pintor , Ambra Demontis , Battista Biggio

Large Language Models (LLMs) are vulnerable to attacks like prompt injection, backdoor attacks, and adversarial attacks, which manipulate prompts or models to generate harmful outputs. In this paper, departing from traditional deep learning…

Computation and Language · Computer Science 2025-02-19 Huawei Lin , Yingjie Lao , Tong Geng , Tan Yu , Weijie Zhao

Large language models (LLMs) have achieved widespread adoption across numerous applications. However, many LLMs are vulnerable to malicious attacks even after safety alignment. These attacks typically bypass LLMs' safety guardrails by…

Cryptography and Security · Computer Science 2025-06-17 Yucheng Li , Surin Ahn , Huiqiang Jiang , Amir H. Abdi , Yuqing Yang , Lili Qiu

Multimodal large language models (MLLMs) are gaining increasing attention. Due to the heterogeneity of their input features, they face significant challenges in terms of jailbreak defenses. Current defense methods rely on costly fine-tuning…

Artificial Intelligence · Computer Science 2026-05-13 Xinyi Zeng , Xue Yang , Jingyuan Zhang , Huanqian Yan , Xiang Chen , Kaiwen Wei , Hankun Kang , Yu Tian

Large language models (LLMs) have shown remarkable capabilities in code generation. However, the effects of hallucinations (e.g., output noise) make it particularly challenging for LLMs to generate high-quality code in one pass. In this…

Software Engineering · Computer Science 2024-09-11 Shuai Wang , Liang Ding , Li Shen , Yong Luo , Zheng He , Wei Yu , Dacheng Tao

Application designers have moved to integrate large language models (LLMs) into their products. However, many LLM-integrated applications are vulnerable to prompt injections. While attempts have been made to address this problem by building…

Cryptography and Security · Computer Science 2025-04-15 Dennis Jacob , Hend Alzahrani , Zhanhao Hu , Basel Alomair , David Wagner

Large language models (LLMs) are increasingly deployed for everyday tasks, including food preparation and health-related guidance. However, food safety remains a high-stakes domain where inaccurate or misleading information can cause severe…

Cryptography and Security · Computer Science 2026-04-06 Weidi Luo , Xiaofei Wen , Tenghao Huang , Hongyi Wang , Zhen Xiang , Chaowei Xiao , Kristina Gligorić , Muhao Chen

Pretrained language models often rely on superficial features that appear predictive during training yet fail to generalize at test time, a phenomenon known as shortcut learning. Existing mitigation methods generally operate at training…

Machine Learning · Computer Science 2026-04-15 Jiayi Li , Shijie Tang , Gün Kaynar , Shiyi Du , Carl Kingsford

Red-teaming has been a widely adopted way to evaluate the harmfulness of Large Language Models (LLMs). It aims to jailbreak a model's safety behavior to make it act as a helpful agent disregarding the harmfulness of the query. Existing…

Computation and Language · Computer Science 2023-11-14 Rishabh Bhardwaj , Soujanya Poria

Large language models (LLMs) are increasingly vulnerable to multi-turn jailbreak attacks, where adversaries iteratively elicit harmful behaviors that bypass single-turn safety filters. Existing defenses predominantly rely on passive…

Cryptography and Security · Computer Science 2025-10-20 ChenYu Wu , Yi Wang , Yang Liao

Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs. Existing approaches overwhelmingly operate within the prompt-optimization paradigm: whether through traditional…

Cryptography and Security · Computer Science 2025-12-18 Rongzhe Wei , Peizhi Niu , Xinjie Shen , Tony Tu , Yifan Li , Ruihan Wu , Eli Chien , Pin-Yu Chen , Olgica Milenkovic , Pan Li

Text-to-image generative models like DALL-E and Stable Diffusion have revolutionized visual content creation across various applications, including advertising, personalized media, and design prototyping. However, crafting effective textual…

Artificial Intelligence · Computer Science 2025-07-22 Donghoon Kim , Minji Bae , Kyuhong Shim , Byonghyo Shim

With the integration of an additional modality, large vision-language models (LVLMs) exhibit greater vulnerability to safety risks (e.g., jailbreaking) compared to their language-only predecessors. Although recent studies have devoted…

Machine Learning · Computer Science 2025-01-07 Ziwei Zheng , Junyao Zhao , Le Yang , Lijun He , Fan Li

Monitoring large language models' (LLMs) activations is an effective way to detect harmful requests before they lead to unsafe outputs. However, traditional safety monitors often require the same amount of compute for every query. This…

Machine Learning · Computer Science 2026-04-22 James Oldfield , Philip Torr , Ioannis Patras , Adel Bibi , Fazl Barez

As LLMs become increasingly prevalent across various applications, it is critical to establish safety guardrails to moderate input/output content of LLMs. Existing guardrail models treat various safety categories independently and fail to…

Artificial Intelligence · Computer Science 2024-07-09 Mintong Kang , Bo Li

As large language models (LLMs) are increasingly integrated into real-world applications, ensuring their safety, robustness, and privacy compliance has become critical. We present OpenGuardrails, the first fully open-source platform that…

Cryptography and Security · Computer Science 2025-10-30 Thomas Wang , Haowen Li

Safety-oriented instruction-following is supposed to keep LLM-controlled robots safe. We show it also creates an availability attack surface. By injecting short safety-plausible phrases (1-5 tokens) into a robots audio channel, an adversary…

Cryptography and Security · Computer Science 2026-04-29 Jonathan Steinberg , Oren Gal

LLM-based coding assistants are seeing rapid adoption, offering substantial gains in developer productivity. As organizations increasingly ship code these agents produce, the security of that code becomes critical. Prior work has shown that…

Cryptography and Security · Computer Science 2026-05-29 Alexander Sternfeld , Andrei Kucharavy , Ljiljana Dolamic

The proliferation of Large Language Models (LLMs) has revolutionized natural language processing and significantly impacted code generation tasks, enhancing software development efficiency and productivity. Notably, LLMs like GPT-4 have…

Software Engineering · Computer Science 2025-03-25 Sheng Ouyang , Yihao Qin , Bo Lin , Liqian Chen , Xiaoguang Mao , Shangwen Wang