English
Related papers

Related papers: Bergeron: Combating Adversarial Attacks through a …

200 papers

Frontier Large Language Models (LLMs) pose unprecedented dual-use risks through the potential proliferation of chemical, biological, radiological, and nuclear (CBRN) weapons knowledge. We present the first comprehensive evaluation of 10…

Cryptography and Security · Computer Science 2025-10-27 Divyanshu Kumar , Nitin Aravind Birur , Tanay Baswa , Sahil Agarwal , Prashanth Harshangi

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

Social alignment in AI systems aims to ensure that these models behave according to established societal values. However, unlike humans, who derive consensus on value judgments through social interaction, current language models (LMs) are…

Computation and Language · Computer Science 2023-10-31 Ruibo Liu , Ruixin Yang , Chenyan Jia , Ge Zhang , Denny Zhou , Andrew M. Dai , Diyi Yang , Soroush Vosoughi

Despite their growing adoption across domains, large language model (LLM)-powered agents face significant security risks from backdoor attacks during training and fine-tuning. These compromised agents can subsequently be manipulated to…

Cryptography and Security · Computer Science 2025-06-12 Li Changjiang , Liang Jiacheng , Cao Bochuan , Chen Jinghui , Wang Ting

The open-sourcing of large language models (LLMs) accelerates application development, innovation, and scientific progress. This includes both base models, which are pre-trained on extensive datasets without alignment, and aligned models,…

Computation and Language · Computer Science 2024-04-17 Xiao Wang , Tianze Chen , Xianjun Yang , Qi Zhang , Xun Zhao , Dahua Lin

The growing integration of Large Language Models (LLMs) into critical societal domains has raised concerns about embedded biases that can perpetuate stereotypes and undermine fairness. Such biases may stem from historical inequalities in…

Computation and Language · Computer Science 2025-10-17 Riccardo Cantini , Alessio Orsino , Massimo Ruggiero , Domenico Talia

The emergence of Large Language Models (LLMs) have fundamentally altered the way we interact with digital systems and have led to the pursuit of LLM powered AI agents to assist in daily workflows. LLMs, whilst powerful and capable of…

Computation and Language · Computer Science 2024-08-05 Prattyush Mangal , Carol Mak , Theo Kanakis , Timothy Donovan , Dave Braines , Edward Pyzer-Knapp

Despite extensive pre-training in moral alignment to prevent generating harmful information, large language models (LLMs) remain vulnerable to jailbreak attacks. In this paper, we propose AutoDefense, a multi-agent defense framework that…

Machine Learning · Computer Science 2024-11-15 Yifan Zeng , Yiran Wu , Xiao Zhang , Huazheng Wang , Qingyun Wu

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

The rapid evolution of artificial intelligence (AI) through developments in Large Language Models (LLMs) and Vision-Language Models (VLMs) has brought significant advancements across various technological domains. While these models enhance…

Computation and Language · Computer Science 2025-11-11 Haibo Jin , Leyang Hu , Xinnuo Li , Peiyan Zhang , Chonghan Chen , Jun Zhuang , Haohan Wang

Open-weight AI systems offer unique benefits, including enhanced transparency, open research, and decentralized access. However, they are vulnerable to tampering attacks which can efficiently elicit harmful behaviors by modifying weights or…

Although pre-trained language models (PrLMs) have achieved significant success, recent studies demonstrate that PrLMs are vulnerable to adversarial attacks. By generating adversarial examples with slight perturbations on different levels…

Computation and Language · Computer Science 2022-08-23 Jiayi Wang , Rongzhou Bao , Zhuosheng Zhang , Hai Zhao

Software systems are increasingly relying on Artificial Intelligence (AI) and Machine Learning (ML) components. The emerging popularity of AI techniques in various application domains attracts malicious actors and adversaries. Therefore,…

Cryptography and Security · Computer Science 2022-02-22 Mohamad Fazelnia , Igor Khokhlov , Mehdi Mirakhorli

Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment. Current approaches rely on sequential adversarial training: generating adversarial prompts and fine-tuning LMs to…

Artificial Intelligence · Computer Science 2026-02-10 Anselm Paulus , Ilia Kulikov , Brandon Amos , Rémi Munos , Ivan Evtimov , Kamalika Chaudhuri , Arman Zharmagambetov

Over the last year, significant advancements have been made in the realms of large language models (LLMs) and multi-modal large language models (MLLMs), particularly in their application to autonomous driving. These models have showcased…

Robotics · Computer Science 2024-06-11 Xiangrui Kong , Thomas Braunl , Marco Fahmi , Yue Wang

Safety aligned Large Language Models (LLMs) are vulnerable to harmful fine-tuning attacks -- a few harmful data mixed in the fine-tuning dataset can break the LLMs's safety alignment. While several defenses have been proposed, our…

Artificial Intelligence · Computer Science 2025-09-08 Tiansheng Huang , Gautam Bhattacharya , Pratik Joshi , Josh Kimball , Ling Liu

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

Aligned LLMs are secure, capable of recognizing and refusing to answer malicious questions. However, the role of internal parameters in maintaining such security is not well understood yet, further these models can be vulnerable to security…

Cryptography and Security · Computer Science 2025-04-08 Shen Li , Liuyi Yao , Lan Zhang , Yaliang Li

Safety alignment in large language models (LLMs) is achieved through fine-tuning mechanisms that regulate neuron activations to suppress harmful content. In this work, we propose a novel approach to induce disalignment by identifying and…

Machine Learning · Computer Science 2025-05-01 Yi Zhou , Wenpeng Xing , Dezhang Kong , Changting Lin , Meng Han

Despite the impressive adaptability of large language models (LLMs), challenges remain in ensuring their security, transparency, and interpretability. Given their susceptibility to adversarial attacks, LLMs need to be defended with an…

Artificial Intelligence · Computer Science 2024-10-11 Tomas Bueno Momcilovic , Beat Buesser , Giulio Zizzo , Mark Purcell , Dian Balta
‹ Prev 1 8 9 10 Next ›