English
Related papers

Related papers: BlackMirror: Black-Box Backdoor Detection for Text…

200 papers

Trojan backdoors can be injected into large language models at various stages, including pretraining, fine-tuning, and in-context learning, posing a significant threat to the model's alignment. Due to the nature of causal language modeling,…

Computation and Language · Computer Science 2025-01-22 Vedant Bhasin , Matthew Yudin , Razvan Stefanescu , Rauf Izmailov

While text-to-image diffusion models demonstrate impressive generation capabilities, they also exhibit vulnerability to backdoor attacks, which involve the manipulation of model outputs through malicious triggers. In this paper, for the…

Computer Vision and Pattern Recognition · Computer Science 2024-07-18 Zhongqi Wang , Jie Zhang , Shiguang Shan , Xilin Chen

Deep learning models have achieved unprecedented performance in the domain of object detection, resulting in breakthroughs in areas such as autonomous driving and security. However, deep learning models are vulnerable to backdoor attacks.…

Computer Vision and Pattern Recognition · Computer Science 2024-06-05 Jeongjin Shin

Recently, it has been shown that deep learning models are vulnerable to Trojan attacks, where an attacker can install a backdoor during training time to make the resultant model misidentify samples contaminated with a small trigger patch.…

Computer Vision and Pattern Recognition · Computer Science 2020-06-11 Haripriya Harikumar , Vuong Le , Santu Rana , Sourangshu Bhattacharya , Sunil Gupta , Svetha Venkatesh

Recent advances in large text-conditional diffusion models have revolutionized image generation by enabling users to create realistic, high-quality images from textual prompts, significantly enhancing artistic creation and visual…

Machine Learning · Computer Science 2025-07-08 Ali Naseh , Jaechul Roh , Eugene Bagdasarian , Amir Houmansadr

Backdoor attacks pose a critical threat by embedding hidden triggers into inputs, causing models to misclassify them into target labels. While extensive research has focused on mitigating these attacks in object recognition models through…

Computer Vision and Pattern Recognition · Computer Science 2025-04-09 Kyle Stein , Andrew Arash Mahyari , Guillermo Francia , Eman El-Sheikh

Multimodal diffusion models for image editing generate outputs conditioned on both textual instructions and visual inputs, aiming to modify target regions while preserving the rest of the image. Although diffusion models have been shown to…

Cryptography and Security · Computer Science 2025-06-02 Ji Guo , Peihong Chen , Wenbo Jiang , Xiaolei Wen , Jiaming He , Jiachen Li , Guoming Lu , Aiguo Chen , Hongwei Li

Backdoor attacks pose a significant threat to the training process of deep neural networks (DNNs). As a widely-used DNN-based application in real-world scenarios, face recognition systems once implanted into the backdoor, may cause serious…

Computer Vision and Pattern Recognition · Computer Science 2024-08-23 Ming Sun , Lihua Jing , Zixuan Zhu , Rui Wang

While effective backdoor detection and inversion schemes have been developed for AIs used e.g. for images, there are challenges in "porting" these methods to LLMs. First, the LLM input space is discrete, which precludes gradient-based…

Machine Learning · Computer Science 2025-09-22 Zhengxing Li , Guangmingmei Yang , Jayaram Raghuram , David J. Miller , George Kesidis

Machine learning has seen tremendous advances in the past few years, which has lead to deep learning models being deployed in varied applications of day-to-day life. Attacks on such models using perturbations, particularly in real-life…

Machine Learning · Computer Science 2020-02-10 Siddhant Bhambri , Sumanyu Muku , Avinash Tulasi , Arun Balaji Buduru

Machine learning systems are vulnerable to backdoor attacks, where attackers manipulate model behavior through data tampering or architectural modifications. Traditional backdoor attacks involve injecting malicious samples with specific…

Cryptography and Security · Computer Science 2025-09-24 Yuan Ma , Jiankang Wei , Yilun Lyu , Kehao Chen , Jingtong Huang

While multimodal contrastive learning methods (e.g., CLIP) can achieve impressive zero-shot classification performance, recent research has revealed that these methods are vulnerable to backdoor attacks. To defend against backdoor attacks…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Yuwei Niu , Shuo He , Qi Wei , Zongyu Wu , Feng Liu , Lei Feng

As object detection becomes integral to many safety-critical applications, understanding its vulnerabilities is essential. Backdoor attacks, in particular, pose a serious threat by implanting hidden triggers in victim models, which…

Cryptography and Security · Computer Science 2025-03-14 Jialin Lu , Junjie Shan , Ziqi Zhao , Ka-Ho Chow

As object detection becomes integral to many safety-critical applications, understanding its vulnerabilities is essential. Backdoor attacks, in particular, pose a serious threat by implanting hidden triggers in victim models, which…

Cryptography and Security · Computer Science 2025-03-17 Jialin Lu , Junjie Shan , Ziqi Zhao , Ka-Ho Chow

Deep neural networks are vulnerable to backdoor attacks, where an adversary manipulates the model behavior through overlaying images with special triggers. Existing backdoor defense methods often require accessing a few validation data and…

Machine Learning · Computer Science 2025-08-20 Tao Sun , Lu Pang , Weimin Lyu , Chao Chen , Haibin Ling

Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs. However, such access may also let malicious actors undermine model safety. To demonstrate the challenge of defending finetuning…

Cryptography and Security · Computer Science 2024-07-01 Danny Halawi , Alexander Wei , Eric Wallace , Tony T. Wang , Nika Haghtalab , Jacob Steinhardt

Visual prompting (VP) is a new technique that adapts well-trained frozen models for source domain tasks to target domain tasks. This study examines VP's benefits for black-box model-level backdoor detection. The visual prompt in VP maps…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Zi-Xuan Huang , Jia-Wei Chen , Zhi-Peng Zhang , Chia-Mu Yu

In this paper, we endeavor to address the challenges of backdoor attacks countermeasures in black-box scenarios, thereby fortifying the security of inference under MLaaS. We first categorize backdoor triggers from a new perspective, i.e.,…

Cryptography and Security · Computer Science 2025-08-06 Ye Li , Chengcheng Zhu , Yanchao Zhao , Jiale Zhang

Backdoor attack is a major threat to deep learning systems in safety-critical scenarios, which aims to trigger misbehavior of neural network models under attacker-controlled conditions. However, most backdoor attacks have to modify the…

Machine Learning · Computer Science 2023-08-24 Yizhen Yuan , Rui Kong , Shenghao Xie , Yuanchun Li , Yunxin Liu

Reliably predicting the behavior of language models -- such as whether their outputs are correct or have been adversarially manipulated -- is a fundamentally challenging task. This is often made even more difficult as frontier language…

Machine Learning · Computer Science 2025-12-02 Dylan Sam , Marc Finzi , J. Zico Kolter