English
Related papers

Related papers: Backdoors in Conditional Diffusion: Threats to Res…

200 papers

An adversarial example is a modified input image designed to cause a Machine Learning (ML) model to make a mistake; these perturbations are often invisible or subtle to human observers and highlight vulnerabilities in a model's ability to…

Cryptography and Security · Computer Science 2024-11-04 Ehsan Ganjidoost , Jeff Orchard

Recent advancements in deep learning-based compression techniques have surpassed traditional methods. However, deep neural networks remain vulnerable to backdoor attacks, where pre-defined triggers induce malicious behaviors. This paper…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Yi Yu , Yufei Wang , Wenhan Yang , Lanqing Guo , Shijian Lu , Ling-Yu Duan , Yap-Peng Tan , Alex C. Kot

Parameter-efficient fine-tuning (PEFT) enables efficient adaptation of pre-trained language models (PLMs) to specific tasks. By tuning only a minimal set of (extra) parameters, PEFT achieves performance that is comparable to standard…

Computation and Language · Computer Science 2024-04-01 Lauren Hong , Ting Wang

Backdoor attacks targeting text-to-image diffusion models have advanced rapidly. However, current backdoor samples often exhibit two key abnormalities compared to benign samples: 1) Semantic Consistency, where backdoor prompts tend to…

Computer Vision and Pattern Recognition · Computer Science 2025-07-25 Jie Zhang , Zhongqi Wang , Shiguang Shan , Xilin Chen

When machine learning training is outsourced to third parties, $backdoor$ $attacks$ become practical as the third party who trains the model may act maliciously to inject hidden behaviors into the otherwise accurate model. Until now, the…

Cryptography and Security · Computer Science 2022-11-16 Sanghyun Hong , Nicholas Carlini , Alexey Kurakin

Vision-Language Models (VLMs) have achieved impressive progress in multimodal text generation, yet their rapid adoption raises increasing concerns about security vulnerabilities. Existing backdoor attacks against VLMs primarily rely on…

Cryptography and Security · Computer Science 2025-12-08 Haoyu Shen , Weimin Lyu , Haotian Xu , Tengfei Ma

Contrastive Language-Image Pre-training (CLIP) on large image-caption datasets has achieved remarkable success in zero-shot classification and enabled transferability to new domains. However, CLIP is extremely more vulnerable to targeted…

Machine Learning · Computer Science 2024-06-12 Wenhan Yang , Jingdong Gao , Baharan Mirzasoleiman

Controllable image synthesis models allow creation of diverse images based on text instructions or guidance from a reference image. Recently, denoising diffusion probabilistic models have been shown to generate more realistic imagery than…

Computer Vision and Pattern Recognition · Computer Science 2022-12-06 Xihui Liu , Dong Huk Park , Samaneh Azadi , Gong Zhang , Arman Chopikyan , Yuxiao Hu , Humphrey Shi , Anna Rohrbach , Trevor Darrell

Clean-label poisoning attacks inject innocuous looking (and "correctly" labeled) poison images into training data, causing a model to misclassify a targeted image after being trained on this data. We consider transferable poisoning attacks…

Machine Learning · Statistics 2019-05-17 Chen Zhu , W. Ronny Huang , Ali Shafahi , Hengduo Li , Gavin Taylor , Christoph Studer , Tom Goldstein

Recently, self-supervised learning (SSL) was shown to be vulnerable to patch-based data poisoning backdoor attacks. It was shown that an adversary can poison a small part of the unlabeled data so that when a victim trains an SSL model on…

Computer Vision and Pattern Recognition · Computer Science 2023-04-05 Ajinkya Tejankar , Maziar Sanjabi , Qifan Wang , Sinong Wang , Hamed Firooz , Hamed Pirsiavash , Liang Tan

Clean-image backdoor attacks, which use only label manipulation in training datasets to compromise deep neural networks, pose a significant threat to security-critical applications. A critical flaw in existing methods is that the poison…

Computer Vision and Pattern Recognition · Computer Science 2025-11-12 Binyan Xu , Fan Yang , Di Tang , Xilin Dai , Kehuan Zhang

Cyber-defense systems are being developed to automatically ingest Cyber Threat Intelligence (CTI) that contains semi-structured data and/or text to populate knowledge graphs. A potential risk is that fake CTI can be generated and spread…

Cryptography and Security · Computer Science 2021-06-22 Priyanka Ranade , Aritran Piplai , Sudip Mittal , Anupam Joshi , Tim Finin

While finetuning AI agents on interaction data -- such as web browsing or tool use -- improves their capabilities, it also introduces critical security vulnerabilities within the agentic AI supply chain. We show that adversaries can…

In recent years there has been enormous interest in vision-language models trained using self-supervised objectives. However, the use of large-scale datasets scraped from the web for training also makes these models vulnerable to potential…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Alvi Md Ishmam , Christopher Thomas

Backdoor attacks threaten the deep learning supply chain by poisoning a small fraction of the training data so that a model behaves normally on clean inputs but misclassifies trigger-carrying inputs to an attacker-chosen target class.…

Cryptography and Security · Computer Science 2026-05-05 Yi Yang , Jinyang Huang , Binbin Liu , Feng-Qi Cui , Xiaokang Zhou , Zhi Liu , Jie Zhang , Meng Li

Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word…

Cryptography and Security · Computer Science 2022-10-21 You Guo , Jun Wang , Trevor Cohn

Backdoor attacks embed malicious triggers into training data, enabling attackers to manipulate neural network behavior during inference while maintaining high accuracy on benign inputs. However, existing backdoor attacks face limitations…

Cryptography and Security · Computer Science 2025-05-27 Zhou Feng , Jiahao Chen , Chunyi Zhou , Yuwen Pu , Qingming Li , Shouling Ji

Diffusion models build a new milestone for image generation yet raising public concerns, for they can be fine-tuned on unauthorized images for customization. Protection based on adversarial attacks rises to encounter this unauthorized…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Boyang Zheng , Chumeng Liang , Xiaoyu Wu

Modern language models remain vulnerable to backdoor attacks via poisoned data, where training inputs containing a trigger are paired with a target output, causing the model to reproduce that behavior whenever the trigger appears at…

Cryptography and Security · Computer Science 2026-01-06 Eric Xue , Ruiyi Zhang , Pengtao Xie

Federated Learning (FL) is a decentralized machine learning method that enables participants to collaboratively train a model without sharing their private data. Despite its privacy and scalability benefits, FL is susceptible to backdoor…

Cryptography and Security · Computer Science 2024-09-11 Yujie Zhang , Neil Gong , Michael K. Reiter