English
Related papers

Related papers: Constitutional Classifiers++: Efficient Production…

200 papers

The proliferation of large language models (LLMs) has underscored concerns regarding their security vulnerabilities, notably against jailbreak attacks, where adversaries design jailbreak prompts to circumvent safety mechanisms for potential…

Cryptography and Security · Computer Science 2025-06-10 Yingchaojie Feng , Zhizhang Chen , Zhining Kang , Sijia Wang , Haoyu Tian , Wei Zhang , Minfeng Zhu , Wei Chen

Large language models (LLMs) have achieved impressive performance across natural language tasks and are increasingly deployed in real-world applications. Despite extensive safety alignment efforts, recent studies show that such alignment is…

Artificial Intelligence · Computer Science 2026-02-02 Yinzhi Zhao , Ming Wang , Shi Feng , Xiaocui Yang , Daling Wang , Yifei Zhang

As large language models (LLMs) become integral to various applications, ensuring both their safety and utility is paramount. Jailbreak attacks, which manipulate LLMs into generating harmful content, pose significant challenges to this…

Cryptography and Security · Computer Science 2025-02-10 Guobin Shen , Dongcheng Zhao , Yiting Dong , Xiang He , Yi Zeng

The problem of adversarial examples, evasion attacks on machine learning classifiers, has proven extremely difficult to solve. This is true even when, as is the case in many practical settings, the classifier is hosted as a remote service…

Cryptography and Security · Computer Science 2019-07-15 Steven Chen , Nicholas Carlini , David Wagner

Deep convolutional neural networks have shown high efficiency in computer visions and other applications. However, with the increase in the depth of the networks, the computational complexity is growing exponentially. In this paper, we…

Machine Learning · Computer Science 2021-01-08 Ali Mirzaeian , Sai Manoj , Ashkan Vakil , Houman Homayoun , Avesta Sasan

Adversarial prompts generated using gradient-based methods exhibit outstanding performance in performing automatic jailbreak attacks against safety-aligned LLMs. Nevertheless, due to the discrete nature of texts, the input gradient of LLMs…

Cryptography and Security · Computer Science 2024-11-04 Qizhang Li , Yiwen Guo , Wangmeng Zuo , Hao Chen

In multiple domains such as malware detection, automated driving systems, or fraud detection, classification algorithms are susceptible to being attacked by malicious agents willing to perturb the value of instance covariates to pursue…

Machine Learning · Statistics 2025-07-10 Victor Gallego , Roi Naveiro , Alberto Redondo , David Rios Insua , Fabrizio Ruggeri

We identify a structural weakness in current large language model (LLM) alignment: modern refusal mechanisms are fail-open. While existing approaches encode refusal behaviors across multiple latent features, suppressing a single dominant…

Machine Learning · Computer Science 2026-02-20 Zachary Coalson , Beth Sohler , Aiden Gabriel , Sanghyun Hong

Robust control barrier functions (CBFs) provide a principled mechanism for smooth safety enforcement under worst-case disturbances. However, existing approaches typically rely on explicit, closed-form structure in the dynamics (e.g.,…

Systems and Control · Electrical Eng. & Systems 2026-04-16 Donggeon David Oh , Duy P. Nguyen , Haimin Hu , Jaime Fernández Fisac

Large language models (LLMs) are increasingly being adopted in a wide range of real-world applications. Despite their impressive performance, recent studies have shown that LLMs are vulnerable to deliberately crafted adversarial prompts…

Artificial Intelligence · Computer Science 2024-06-17 Wei Zhao , Zhe Li , Yige Li , Ye Zhang , Jun Sun

Although Large Language Models (LLMs) have demonstrated significant capabilities in executing complex tasks in a zero-shot manner, they are susceptible to jailbreak attacks and can be manipulated to produce harmful outputs. Recently, a…

Cryptography and Security · Computer Science 2024-11-07 Zhao Xu , Fan Liu , Hao Liu

As large language models (LLMs) become increasingly prevalent and integrated into autonomous systems, ensuring their safety is imperative. Despite significant strides toward safety alignment, recent work GCG~\citep{zou2023universal}…

Computation and Language · Computer Science 2024-11-26 Zeyi Liao , Huan Sun

Recent advances in large vision-language models (VLMs) have demonstrated remarkable success across a wide range of visual understanding tasks. However, the robustness of these models against jailbreak attacks remains an open challenge. In…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Xiangyu Yin , Jiaxu Liu , Zhen Chen , Jinwei Hu , Yi Dong , Xiaowei Huang , Wenjie Ruan

Backdoor attacks have become a major security threat for deploying machine learning models in security-critical applications. Existing research endeavors have proposed many defenses against backdoor attacks. Despite demonstrating certain…

Machine Learning · Computer Science 2023-11-28 Hengzhi Pei , Jinyuan Jia , Wenbo Guo , Bo Li , Dawn Song

Many recent works have proposed methods to train classifiers with local robustness properties, which can provably eliminate classes of evasion attacks for most inputs, but not all inputs. Since data distribution shift is very common in…

Cryptography and Security · Computer Science 2021-12-03 Yizheng Chen , Shiqi Wang , Yue Qin , Xiaojing Liao , Suman Jana , David Wagner

The discovery of "jailbreaks" to bypass safety filters of Large Language Models (LLMs) and harmful responses have encouraged the community to implement safety measures. One major safety measure is to proactively test the LLMs with…

Machine Learning · Computer Science 2025-11-10 Haibo Jin , Ruoxi Chen , Peiyan Zhang , Andy Zhou , Haohan Wang

Despite the rapid development of safety alignment techniques for LLMs, defending against multi-turn jailbreaks is still a challenging task. In this paper, we conduct a comprehensive comparison, revealing that some existing defense methods…

Cryptography and Security · Computer Science 2025-12-29 Xiaoya Lu , Dongrui Liu , Yi Yu , Luxin Xu , Jing Shao

Machine-learning models for security-critical applications such as bot, malware, or spam detection, operate in constrained discrete domains. These applications would benefit from having provable guarantees against adversarial examples. The…

Machine Learning · Computer Science 2019-07-02 Bogdan Kulynych , Jamie Hayes , Nikita Samarin , Carmela Troncoso

AI systems can take harmful actions and are highly vulnerable to adversarial attacks. We present an approach, inspired by recent advances in representation engineering, that interrupts the models as they respond with harmful outputs with…

As frontier AI models are deployed in high-stakes decision pipelines, their ability to maintain metacognitive stability (knowing what they do not know, detecting errors, seeking clarification) under adversarial pressure is a critical safety…

Artificial Intelligence · Computer Science 2026-05-15 Rahul Kumar
‹ Prev 1 8 9 10 Next ›