English
Related papers

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

200 papers

Backdoor (trojan) attacks embed hidden, controllable behaviors into machine-learning models so that models behave normally on benign inputs but produce attacker-chosen outputs when a trigger is present. This survey reviews the rapidly…

Cryptography and Security · Computer Science 2025-09-10 Bilal Hussain Abbasi , Yanjun Zhang , Leo Zhang , Shang Gao

Deep neural network (DNN) models have become prevalent in edge devices for real-time inference. However, they are vulnerable to model extraction attacks and require protection. Existing defense approaches either fail to fully safeguard…

Cryptography and Security · Computer Science 2023-11-17 Ziyu Liu , Yukui Luo , Shijin Duan , Tong Zhou , Xiaolin Xu

Deep learning models have been shown to be vulnerable to recent backdoor attacks. A backdoored model behaves normally for inputs containing no attacker-secretly-chosen trigger and maliciously for inputs with the trigger. To date, backdoor…

Computer Vision and Pattern Recognition · Computer Science 2022-05-31 Hua Ma , Yinshan Li , Yansong Gao , Alsharif Abuadbba , Zhi Zhang , Anmin Fu , Hyoungshick Kim , Said F. Al-Sarawi , Nepal Surya , Derek Abbott

Text-to-image (T2I) models have raised increasing safety concerns due to their capacity to generate NSFW and other banned objects. To mitigate these risks, safety filters and concept removal techniques have been introduced to block…

Cryptography and Security · Computer Science 2026-01-13 Xi Ye , Yiwen Liu , Lina Wang , Run Wang , Geying Yang , Yufei Hou , Jiayi Yu

A fundamental issue in deep learning has been adversarial robustness. As these systems have scaled, such issues have persisted. Currently, large language models (LLMs) with billions of parameters suffer from adversarial attacks just like…

Machine Learning · Computer Science 2025-02-11 Brian Formento , Chuan Sheng Foo , See-Kiong Ng

Detecting semantic backdoors in classification models--where some classes can be activated by certain natural, but out-of-distribution inputs--is an important problem that has received relatively little attention. Semantic backdoors are…

Machine Learning · Computer Science 2026-01-08 Arpad Berta , Gabor Danner , Istvan Hegedus , Mark Jelasity

Warning: this paper contains content that may be inappropriate or offensive. As generative models become available for public use in various applications, testing and analyzing vulnerabilities of these models has become a priority. In this…

Artificial Intelligence · Computer Science 2024-11-11 Ninareh Mehrabi , Palash Goyal , Christophe Dupuy , Qian Hu , Shalini Ghosh , Richard Zemel , Kai-Wei Chang , Aram Galstyan , Rahul Gupta

Adversarial examples are well-known tools to evaluate the vulnerability of deep neural networks (DNNs). Although lots of adversarial attack algorithms have been developed, it's still challenging in the practical scenario that the model's…

Cryptography and Security · Computer Science 2025-05-27 Meixi Zheng , Xuanchen Yan , Zihao Zhu , Hongrui Chen , Baoyuan Wu

Autoregressive Visual Language Models (VLMs) showcase impressive few-shot learning capabilities in a multimodal context. Recently, multimodal instruction tuning has been proposed to further enhance instruction-following abilities. However,…

Computer Vision and Pattern Recognition · Computer Science 2024-02-22 Jiawei Liang , Siyuan Liang , Man Luo , Aishan Liu , Dongchen Han , Ee-Chien Chang , Xiaochun Cao

Deep learning has demonstrated state-of-the-art performance for a variety of challenging computer vision tasks. On one hand, this has enabled deep visual models to pave the way for a plethora of critical applications like disease…

Machine Learning · Computer Science 2020-06-29 Mohammad A. A. K. Jalwana , Naveed Akhtar , Mohammed Bennamoun , Ajmal Mian

In Machine Learning, White Box Adversarial Attacks rely on knowing underlying knowledge about the model attributes. This works focuses on discovering to distrinct pieces of model information: the underlying architecture and primary training…

Machine Learning · Computer Science 2020-09-08 Josh Kalin , Matthew Ciolino , David Noever , Gerry Dozier

Recent advancements in diffusion models have enabled high-fidelity and photorealistic image generation across diverse applications. However, these models also present security and privacy risks, including copyright violations, sensitive…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Jiacheng Shi , Yanfu Zhang , Huajie Shao , Ashley Gao

Backdoor attacks have been shown to be a serious security threat against deep learning models, and detecting whether a given model has been backdoored becomes a crucial task. Existing defenses are mainly built upon the observation that the…

Cryptography and Security · Computer Science 2022-08-16 Tong Wang , Yuan Yao , Feng Xu , Miao Xu , Shengwei An , Ting Wang

We revisit language bottleneck models as an approach to ensuring the explainability of deep learning models for image classification. Because of inevitable information loss incurred in the step of converting images into language, the…

Computer Vision and Pattern Recognition · Computer Science 2024-06-25 Honori Udo , Takafumi Koshinaka

Backdoor attacks have severely threatened deep neural network (DNN) models in the past several years. These attacks can occur in almost every stage of the deep learning pipeline. Although the attacked model behaves normally on benign…

Computer Vision and Pattern Recognition · Computer Science 2024-05-21 Yangming Chen

Multi-modal large language models (MLLMs), capable of processing text, images, and audio, have been widely adopted in various AI applications. However, recent MLLMs integrating images and text remain highly vulnerable to coordinated…

Cryptography and Security · Computer Science 2025-12-19 Zihao Wang , Kar Wai Fok , Vrizlynn L. L. Thing

Multimodal large language models (MLLMs) have become integral to a wide range of real-world applications by jointly reasoning over text and visual inputs. However, despite recent advances in safety alignment, MLLMs remain vulnerable to…

Cryptography and Security · Computer Science 2026-03-10 Xinkai Wang , Beibei Li , Zerui Shao , Ao Liu , Guangquan Xu , Shouling Ji

Modern image-to-text systems typically adopt the encoder-decoder framework, which comprises two main components: an image encoder, responsible for extracting image features, and a transformer-based decoder, used for generating captions.…

Computer Vision and Pattern Recognition · Computer Science 2023-07-20 Raz Lapid , Moshe Sipper

Deep neural networks (DNNs) are vulnerable to backdoor attacks which can hide backdoor triggers in DNNs by poisoning training data. A backdoored model behaves normally on clean test images, yet consistently predicts a particular target…

Computer Vision and Pattern Recognition · Computer Science 2020-06-17 Shihao Zhao , Xingjun Ma , Xiang Zheng , James Bailey , Jingjing Chen , Yu-Gang Jiang

The advent of multimodal deep learning models, such as CLIP, has unlocked new frontiers in a wide range of applications, from image-text understanding to classification tasks. However, these models are not safe for adversarial attacks,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Md. Iqbal Hossain , Afia Sajeeda , Neeresh Kumar Perla , Ming Shao
‹ Prev 1 4 5 6 7 8 10 Next ›