English
Related papers

Related papers: Constitutional Classifiers++: Efficient Production…

200 papers

Large language models (LLMs) are widely used for task understanding and action planning in embodied intelligence (EI) systems, but their adoption substantially increases vulnerability to jailbreak attacks. While recent work explores…

Cryptography and Security · Computer Science 2026-01-06 Jirui Yang , Zheyu Lin , Zhihui Lu , Yinggui Wang , Lei Wang , Tao Wei , Qiang Duan , Xin Du , Shuhan Yang

We address jailbreaks, backdoors, and unlearning for large language models (LLMs). Unlike prior work, which trains LLMs based on their actions when given malign instructions, our method specifically trains the model to change how it…

Machine Learning · Computer Science 2026-04-14 Eric Easley , Sebastian Farquhar

The adoption of large language models (LLMs) in many applications, from customer service chat bots and software development assistants to more capable agentic systems necessitates research into how to secure these systems. Attacks like…

Cryptography and Security · Computer Science 2024-12-03 Erick Galinkin , Martin Sablotny

We present a theoretical analysis and empirical evaluations of a novel set of techniques for computational cost reduction of classifiers that are based on learned transform and soft-threshold. By modifying optimization procedures for…

Federated learning (FL) enables privacy-preserving model training by keeping data decentralized. However, it remains vulnerable to label-flipping attacks, where malicious clients manipulate labels to poison the global model. Despite their…

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

While Large Language Models (LLMs) demonstrate remarkable capabilities, they remain susceptible to sophisticated, multi-step jailbreak attacks that circumvent conventional surface-level safety alignment by exploiting the internal generation…

Machine Learning · Computer Science 2026-05-21 Jiachen Ma , Jiawen Zhang , Xiangtian Li , Bo Zou , Chaochao Lu , Chao Yang

Jailbreak attacks aim to bypass the LLMs' safeguards. While researchers have proposed different jailbreak attacks in depth, they have done so in isolation -- either with unaligned settings or comparing a limited range of methods. To fill…

Cryptography and Security · Computer Science 2025-05-27 Junjie Chu , Yugeng Liu , Ziqing Yang , Xinyue Shen , Michael Backes , Yang Zhang

Large Vision-Language Models (LVLMs), trained on multimodal big datasets, have significantly advanced AI by excelling in vision-language tasks. However, these models remain vulnerable to adversarial attacks, particularly jailbreak attacks,…

Computer Vision and Pattern Recognition · Computer Science 2024-09-12 Md Zarif Hossain , Ahmed Imteaj

Deep neural networks are vulnerable to adversarial examples, i.e., carefully-crafted inputs that mislead classification at test time. Recent defenses have been shown to improve adversarial robustness by detecting anomalous deviations from…

Machine Learning · Computer Science 2020-10-20 Francesco Crecchi , Marco Melis , Angelo Sotgiu , Davide Bacciu , Battista Biggio

Machine learning is a powerful tool enabling full automation of a huge number of tasks without explicit programming. Despite recent progress of machine learning in different domains, these models have shown vulnerabilities when they are…

Machine Learning · Computer Science 2026-03-27 Mohammad Meymani , Roozbeh Razavi-Far

With the growing deployment of LLMs in daily applications like chatbots and content generation, efforts to ensure outputs align with human values and avoid harmful content have intensified. However, increasingly sophisticated jailbreak…

Cryptography and Security · Computer Science 2025-06-10 Cheng Qian , Hainan Zhang , Lei Sha , Zhiming Zheng

While Large Language Models (LLMs) have achieved tremendous success in various applications, they are also susceptible to jailbreaking attacks. Several primary defense strategies have been proposed to protect LLMs from producing harmful…

Machine Learning · Computer Science 2024-11-01 Yichuan Mo , Yuji Wang , Zeming Wei , Yisen Wang

Safety alignment mechanism are essential for preventing large language models (LLMs) from generating harmful information or unethical content. However, cleverly crafted prompts can bypass these safety measures without accessing the model's…

Computation and Language · Computer Science 2025-01-31 Sunbowen Lee , Shiwen Ni , Chi Wei , Shuaimin Li , Liyang Fan , Ahmadreza Argha , Hamid Alinejad-Rokny , Ruifeng Xu , Yicheng Gong , Min Yang

We propose a novel and low-cost test-time adversarial defense by devising interpretability-guided neuron importance ranking methods to identify neurons important to the output classes. Our method is a training-free approach that can…

Computer Vision and Pattern Recognition · Computer Science 2024-09-24 Akshay Kulkarni , Tsui-Wei Weng

Adversarial training instances can severely distort a model's behavior. This work investigates certified regression defenses, which provide guaranteed limits on how much a regressor's prediction may change under a poisoning attack. Our key…

Machine Learning · Computer Science 2023-01-02 Zayd Hammoudeh , Daniel Lowd

Neural network classifiers are vulnerable to data poisoning attacks, as attackers can degrade or even manipulate their predictions thorough poisoning only a few training samples. However, the robustness of heuristic defenses is hard to…

Machine Learning · Computer Science 2020-10-14 Ruoxin Chen , Jie Li , Chentao Wu , Bin Sheng , Ping Li

Despite prior safety alignment efforts, mainstream LLMs can still generate harmful and unethical content when subjected to jailbreaking attacks. Existing jailbreaking methods fall into two main categories: template-based and…

Artificial Intelligence · Computer Science 2025-04-03 Weipeng Jiang , Zhenting Wang , Juan Zhai , Shiqing Ma , Zhengyu Zhao , Chao Shen

Despite extensive safety-tuning, large language models (LLMs) remain vulnerable to jailbreak attacks via adversarially crafted instructions, reflecting a persistent trade-off between safety and task performance. In this work, we propose…

Cryptography and Security · Computer Science 2025-08-26 Wei Jie Yeo , Ranjan Satapathy , Erik Cambria

Despite extensive safety alignment, Large Language Models (LLMs) often fail against jailbreak attacks. While machine unlearning has emerged as a promising defense by erasing specific harmful parameters, current methods remain vulnerable to…

Cryptography and Security · Computer Science 2026-01-07 Xi Wang , Songlei Jian , Shasha Li , Xiaopeng Li , Zhaoye Li , Bin Ji , Baosheng Wang , Jie Yu