English
Related papers

Related papers: REFORGE: Multi-modal Attacks Reveal Vulnerable Con…

200 papers

The widespread adoption of deep learning across various industries has introduced substantial challenges, particularly in terms of model explainability and security. The inherent complexity of deep learning models, while contributing to…

Cryptography and Security · Computer Science 2025-01-08 Kealan Dunnett , Reza Arablouei , Dimity Miller , Volkan Dedeoglu , Raja Jurdak

Adversarial attacks, particularly the Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) pose significant threats to the robustness of deep learning models in image classification. This paper explores and refines defense…

Cryptography and Security · Computer Science 2025-05-15 Hetvi Waghela , Jaydip Sen , Sneha Rakshit

Retrieval-Augmented Generation (RAG) significantly mitigates the hallucinations and domain knowledge deficiency in large language models by incorporating external knowledge bases. However, the multi-module architecture of RAG introduces…

Cryptography and Security · Computer Science 2026-03-24 Yanming Mu , Hao Hu , Feiyang Li , Qiao Yuan , Jiang Wu , Zichuan Liu , Pengcheng Liu , Mei Wang , Hongwei Zhou , Yuling Liu

Diffusion models are renowned for their state-of-the-art performance in generating synthetic images. However, concerns related to safety, privacy, and copyright highlight the need for machine unlearning, which can make diffusion models…

Machine Learning · Computer Science 2025-12-04 Xun Yuan , Zilong Zhao , Jiayu Li , Aryan Pasikhani , Prosanta Gope , Biplab Sikdar

Here, we show that current LLM unlearning methods inherently reduce models' robustness, causing them to misbehave even when a single non-adversarial forget-token is present in the retain-query. Toward understanding underlying causes, we…

Computation and Language · Computer Science 2026-04-21 Dang Huu-Tien , Hoang Thanh-Tung , Anh Bui , Minh-Phuong Nguyen , Le-Minh Nguyen , Naoya Inoue

In recent years, deep neural network approaches have been widely adopted for machine learning tasks, including classification. However, they were shown to be vulnerable to adversarial perturbations: carefully crafted small perturbations can…

Computer Vision and Pattern Recognition · Computer Science 2018-05-21 Pouya Samangouei , Maya Kabkab , Rama Chellappa

Text-to-image (T2I) models such as Stable Diffusion have advanced rapidly and are now widely used in content creation. However, these models can be misused to generate harmful content, including nudity or violence, posing significant safety…

Cryptography and Security · Computer Science 2025-06-13 Zilong Wang , Xiang Zheng , Xiaosen Wang , Bo Wang , Xingjun Ma , Yu-Gang Jiang

Large-scale generative models have shown impressive image-generation capabilities, propelled by massive data. However, this often inadvertently leads to the generation of harmful or inappropriate content and raises copyright concerns.…

Machine Learning · Computer Science 2025-03-11 Myeongseob Ko , Henry Li , Zhun Wang , Jonathan Patsenker , Jiachen T. Wang , Qinbin Li , Ming Jin , Dawn Song , Ruoxi Jia

Text-to-image (T2I) diffusion models have achieved remarkable success in generating high-quality images from textual prompts. However, their ability to store vast amounts of knowledge raises concerns in scenarios where selective forgetting…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Gen Li , Yang Xiao , Jie Ji , Kaiyuan Deng , Bo Hui , Linke Guo , Xiaolong Ma

The vulnerability of Deep Neural Networks (DNNs) to adversarial examples has been confirmed. Existing adversarial defenses primarily aim at preventing adversarial examples from attacking DNNs successfully, rather than preventing their…

Computer Vision and Pattern Recognition · Computer Science 2023-03-09 Jinwei Wang , Hao Wu , Haihua Wang , Jiawei Zhang , Xiangyang Luo , Bin Ma

Large language models (LLMs) excel in various tasks but remain vulnerable to jailbreak attacks, where adversaries manipulate prompts to generate harmful outputs. Examining jailbreak prompts helps uncover the shortcomings of LLMs. However,…

Computation and Language · Computer Science 2024-12-18 Weixiong Zheng , Peijian Zeng , Yiwei Li , Hongyan Wu , Nankai Lin , Junhao Chen , Aimin Yang , Yongmei Zhou

We explore adversarial attacks against retrieval-augmented generation (RAG) systems to identify their vulnerabilities. We focus on generating human-imperceptible adversarial examples and introduce a novel imperceptible retrieve-to-generate…

Information Retrieval · Computer Science 2025-05-29 Hongru Song , Yu-an Liu , Ruqing Zhang , Jiafeng Guo , Jianming Lv , Maarten de Rijke , Xueqi Cheng

We present UniGen-1.5, a unified multimodal large language model (MLLM) for advanced image understanding, generation and editing. Building upon UniGen, we comprehensively enhance the model architecture and training pipeline to strengthen…

Computer Vision and Pattern Recognition · Computer Science 2025-11-19 Rui Tian , Mingfei Gao , Haiming Gang , Jiasen Lu , Zhe Gan , Yinfei Yang , Zuxuan Wu , Afshin Dehghan

Invisible watermarking for autoregressive (AR) image generation has recently gained attention as a means of protecting image ownership and tracing AI-generated content. However, existing approaches suffer from three key limitations: (1)…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Yigit Yilmaz , Elena Petrova , Mehmet Kaya , Lucia Rossi , Amir Rahman

Large Language Models (LLMs) have demonstrated impressive capabilities in natural language tasks, but their safety and morality remain contentious due to their training on internet text corpora. To address these concerns, alignment…

Computation and Language · Computer Science 2024-08-06 Mohammad Bahrami Karkevandi , Nishant Vishwamitra , Peyman Najafirad

Retrieval-Augmented Generation (RAG) enriches LLMs by dynamically retrieving external knowledge, reducing hallucinations and satisfying real-time information needs. While existing research mainly targets RAG's performance and efficiency,…

Information Retrieval · Computer Science 2025-12-29 Zhuo Chen , Yuyang Gong , Jiawei Liu , Miaokun Chen , Haotan Liu , Qikai Cheng , Fan Zhang , Wei Lu , Xiaozhong Liu

Multimodal large language models (MLLMs) have achieved impressive performance across diverse tasks by jointly reasoning over textual and visual inputs. Despite their success, these models remain highly vulnerable to adversarial…

Machine Learning · Computer Science 2025-11-03 Guangzhi Su , Shuchang Huang , Yutong Ke , Zhuohang Liu , Long Qian , Kaizhu Huang

Graph Neural Networks (GNNs) have demonstrated significant application potential in various fields. However, GNNs are still vulnerable to adversarial attacks. Numerous adversarial defense methods on GNNs are proposed to address the problem…

Social and Information Networks · Computer Science 2024-06-21 Tao Wu , Xinwen Cao , Chao Wang , Shaojie Qiao , Xingping Xian , Lin Yuan , Canyixing Cui , Yanbing Liu

Researches have shown that deep neural networks are vulnerable to malicious attacks, where adversarial images are created to trick a network into misclassification even if the images may give rise to totally different labels by human eyes.…

Computer Vision and Pattern Recognition · Computer Science 2022-05-11 Yuzhen Ding , Nupur Thakur , Baoxin Li

Despite being popularly used in many applications, neural network models have been found to be vulnerable to adversarial examples, i.e., carefully crafted examples aiming to mislead machine learning models. Adversarial examples can pose…

Machine Learning · Computer Science 2019-07-30 Siwakorn Srisakaokul , Yuhao Zhang , Zexuan Zhong , Wei Yang , Tao Xie , Bo Li