English
Related papers

Related papers: Robust Anti-Backdoor Instruction Tuning in LVLMs

200 papers

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

In the field of natural language processing, the prevalent approach involves fine-tuning pretrained language models (PLMs) using local samples. Recent research has exposed the susceptibility of PLMs to backdoor attacks, wherein the…

Machine Learning · Computer Science 2023-10-31 Ruixiang Tang , Jiayi Yuan , Yiming Li , Zirui Liu , Rui Chen , Xia Hu

Instruction-following language models are trained to be helpful and safe, yet their safety behavior can deteriorate under benign fine-tuning and worsen under adversarial updates. Existing defenses often offer limited protection or force a…

Computation and Language · Computer Science 2026-05-12 Jyotin Goel , Souvik Maji , Pratik Mazumder

Multimodal large language models (MLLMs) comprise of both visual and textual modalities to process vision language tasks. However, MLLMs are vulnerable to security-related issues, such as jailbreak attacks that alter the model's input to…

Cryptography and Security · Computer Science 2025-10-27 Xingwei Zhong , Kar Wai Fok , Vrizlynn L. L. Thing

Large pre-trained models have achieved notable success across a range of downstream tasks. However, recent research shows that a type of adversarial attack ($\textit{i.e.,}$ backdoor attack) can manipulate the behavior of machine learning…

Artificial Intelligence · Computer Science 2024-10-29 Dongliang Guo , Mengxuan Hu , Zihan Guan , Junfeng Guo , Thomas Hartvigsen , Sheng Li

Vision-Language adaptation (VL adaptation) transforms Large Language Models (LLMs) into Large Vision-Language Models (LVLMs) for multimodal tasks, but this process often compromises the inherent safety capabilities embedded in the original…

Computation and Language · Computer Science 2024-11-18 Seongyun Lee , Geewook Kim , Jiyeon Kim , Hyunji Lee , Hoyeon Chang , Sue Hyun Park , Minjoon Seo

Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails. In many domains, adversarial training has proven to be one of the most promising methods to reliably improve robustness against such…

Machine Learning · Computer Science 2024-11-04 Sophie Xhonneux , Alessandro Sordoni , Stephan Günnemann , Gauthier Gidel , Leo Schwinn

Large Language Models (LLMs) are highly vulnerable to input perturbations, as even a small prompt change may result in a substantially different output. Existing methods to enhance LLM robustness are primarily focused on perturbed data…

Computation and Language · Computer Science 2025-04-04 Aryan Agrawal , Lisa Alazraki , Shahin Honarvar , Marek Rei

Releasing open-source large language models (LLMs) presents a dual-use risk since bad actors can easily fine-tune these models for harmful purposes. Even without the open release of weights, weight stealing and fine-tuning APIs make closed…

Despite advances in AI alignment, large language models (LLMs) remain vulnerable to adversarial attacks or jailbreaking, in which adversaries can modify prompts to induce unwanted behavior. While some defenses have been proposed, they have…

Machine Learning · Computer Science 2024-11-11 Andy Zhou , Bo Li , Haohan Wang

The widespread use of Vision Language Models (VLMs, e.g. CLIP) has raised concerns about their vulnerability to sophisticated and imperceptible adversarial attacks. These attacks could compromise model performance and system security in…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Xiaowei Fu , Lei Zhang

Large vision-language models (LVLMs) have demonstrated their incredible capability in image understanding and response generation. However, this rich visual interaction also makes LVLMs vulnerable to adversarial examples. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2024-06-27 Xunguang Wang , Zhenlan Ji , Pingchuan Ma , Zongjie Li , Shuai Wang

Backdoor attacks compromise model reliability by using triggers to manipulate outputs. Trigger inversion can accurately locate these triggers via a generator and is therefore critical for backdoor defense. However, the discrete nature of…

Cryptography and Security · Computer Science 2026-03-18 Ruyi Zhang , Heng Gao , Songlei Jian , Yusong Tan , Haifang Zhou

With the rise of advanced reasoning capabilities, large language models (LLMs) are receiving increasing attention. However, although reasoning improves LLMs' performance on downstream tasks, it also introduces new security risks, as…

Cryptography and Security · Computer Science 2025-10-10 Man Hu , Xinyi Wu , Zuofeng Suo , Jinbo Feng , Linghui Meng , Yanhao Jia , Anh Tuan Luu , Shuai Zhao

Large vision language models (LVLMs) have demonstrated impressive performance across a wide range of tasks. These capabilities largely stem from visual instruction tuning, which fine-tunes models on datasets consisting of curated…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Myeongkyun Kang , Soopil Kim , Xiaoxiao Li , Sang Hyun Park

Large vision-language models (LVLMs) have achieved impressive performance across a wide range of vision-language tasks, while they remain vulnerable to backdoor attacks. Existing backdoor attacks on LVLMs aim to force the victim model to…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Zhifang Zhang , Qiqi Tao , Jiaqi Lv , Na Zhao , Lei Feng , Joey Tianyi Zhou

Large Language Models (LLMs) have emerged as powerful tools, but their inherent safety risks - ranging from harmful content generation to broader societal harms - pose significant challenges. These risks can be amplified by the recent…

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across various tasks, yet they remain vulnerable to backdoor attacks. Existing defense methods predominantly focus on sample-level defense, which relies on the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Xuanyu Ge , Zhongqi Wang , Jie Zhang , Shiguang Shan , Xilin Chen

Fine-tuning lets practitioners repurpose aligned large language models (LLMs) for new domains, yet recent work reveals emergent misalignment (EMA): Even a small, domain-specific fine-tune can induce harmful behaviors far outside the target…

Machine Learning · Computer Science 2026-03-06 David Kaczér , Magnus Jørgenvåg , Clemens Vetter , Esha Afzal , Robin Haselhorst , Lucie Flek , Florian Mai

The integration of additional modalities increases the susceptibility of large vision-language models (LVLMs) to safety risks, such as jailbreak attacks, compared to their language-only counterparts. While existing research primarily…

Computation and Language · Computer Science 2025-06-24 Yilei Jiang , Xinyan Gao , Tianshuo Peng , Yingshui Tan , Xiaoyong Zhu , Bo Zheng , Xiangyu Yue