English
Related papers

Related papers: Shifting the Gradient: Understanding How Defensive…

200 papers

As large language models (LLMs) grow more capable, concerns about their safe deployment have also grown. Although alignment mechanisms have been introduced to deter misuse, they remain vulnerable to carefully designed adversarial prompts.…

Computation and Language · Computer Science 2025-08-19 Xinbo Wu , Abhishek Umrawal , Lav R. Varshney

Vision-language pre-training models (VLPs) have exhibited revolutionary improvements in various vision-language tasks. In VLP, some adversarial attacks fool a model into false or absurd classifications. Previous studies addressed these…

Computer Vision and Pattern Recognition · Computer Science 2023-09-07 Hiroki Azuma , Yusuke Matsui

Large Language Models (LLMs) are increasingly integrated into daily routines, yet they raise significant privacy and safety concerns. Recent research proposes collaborative inference, which outsources the early-layer inference to ensure…

Cryptography and Security · Computer Science 2025-07-23 Tian Dong , Yan Meng , Shaofeng Li , Guoxing Chen , Zhen Liu , Haojin Zhu

Previous work has showcased the intriguing capabilities of Large Language Models (LLMs) in instruction-following and rhetorical fluency. However, systematic exploration of their dual capabilities to autonomously persuade and resist…

Computation and Language · Computer Science 2025-06-10 Tianjie Ju , Yujia Chen , Hao Fei , Mong-Li Lee , Wynne Hsu , Pengzhou Cheng , Zongru Wu , Zhuosheng Zhang , Gongshen Liu

Prompt injection attacks pose a critical threat to large language models (LLMs), enabling goal hijacking and data leakage. Prompt guard models, though effective in defense, suffer from over-defense -- falsely flagging benign inputs as…

Computation and Language · Computer Science 2025-04-01 Hao Li , Xiaogeng Liu

Policy gradient algorithms have driven many recent advancements in language model reasoning. An appealing property is their ability to learn from exploration on their own trajectories, a process crucial for fostering diverse and creative…

Machine Learning · Computer Science 2026-03-13 Aleksei Petrenko , Ben Lipkin , Kevin Chen , Erik Wijmans , Marco Cusumano-Towner , Raja Giryes , Philipp Krähenbühl

Prepending model inputs with safety prompts is a common practice for safeguarding large language models (LLMs) against queries with harmful intents. However, the underlying working mechanisms of safety prompts have not been unraveled yet,…

Machine Learning · Computer Science 2024-06-04 Chujie Zheng , Fan Yin , Hao Zhou , Fandong Meng , Jie Zhou , Kai-Wei Chang , Minlie Huang , Nanyun Peng

Contrastive learning models have demonstrated impressive abilities to capture semantic similarities by aligning representations in the embedding space. However, their performance can be limited by the quality of the training data and its…

Computer Vision and Pattern Recognition · Computer Science 2025-03-27 Amirabbas Afzali , Borna Khodabandeh , Ali Rasekh , Mahyar JafariNodeh , Sepehr kazemi , Simon Gottschalk

Backdoor attacks are a significant threat to the performance and integrity of pre-trained language models. Although such models are routinely fine-tuned for downstream NLP tasks, recent work shows they remain vulnerable to backdoor attacks…

Machine Learning · Computer Science 2025-08-28 Santosh Chapagain , Shah Muhammad Hamdi , Soukaina Filali Boubrahimi

Federated Learning(FL), in theory, preserves privacy of individual clients' data while producing quality machine learning models. However, attacks such as Deep Leakage from Gradients(DLG) severely question the practicality of FL. In this…

Machine Learning · Computer Science 2024-08-19 Joon Kim , Sejin Park

While Large Language Models (LLMs) have achieved tremendous success in various applications, they are also susceptible to jailbreaking attacks. Several primary defense strategies have been proposed to protect LLMs from producing harmful…

Machine Learning · Computer Science 2024-11-01 Yichuan Mo , Yuji Wang , Zeming Wei , Yisen Wang

With the development of deep learning technology, the facial manipulation system has become powerful and easy to use. Such systems can modify the attributes of the given facial images, such as hair color, gender, and age. Malicious…

Computer Vision and Pattern Recognition · Computer Science 2023-03-22 Yao Zhu , Yuefeng Chen , Xiaodan Li , Rong Zhang , Xiang Tian , Bolun Zheng , Yaowu Chen

Training generative models with differential privacy (DP) typically involves injecting noise into gradient updates or adapting the discriminator's training procedure. As a result, such approaches often struggle with hyper-parameter tuning…

Machine Learning · Computer Science 2024-10-29 Kristjan Greenewald , Yuancheng Yu , Hao Wang , Kai Xu

The increasing need for sharing healthcare data and collaborating on clinical research has raised privacy concerns. Health information leakage due to malicious attacks can lead to serious problems such as misdiagnoses and patient…

Computer Vision and Pattern Recognition · Computer Science 2025-03-24 Shiyi Jiang , Farshad Firouzi , Krishnendu Chakrabarty

Masked Language Model (MLM) framework has been widely adopted for self-supervised language pre-training. In this paper, we argue that randomly sampled masks in MLM would lead to undesirably large gradient variance. Thus, we theoretically…

Computation and Language · Computer Science 2020-10-15 Mingzhi Zheng , Dinghan Shen , Yelong Shen , Weizhu Chen , Lin Xiao

Large language models (LLMs) have demonstrated impressive performance on a number of natural language processing tasks, such as question answering and text summarization. However, their performance on sequence labeling tasks such as intent…

Computation and Language · Computer Science 2024-02-27 Yao Qiang , Subhrangshu Nandi , Ninareh Mehrabi , Greg Ver Steeg , Anoop Kumar , Anna Rumshisky , Aram Galstyan

Neural networks (NNs) are already deployed in hardware today, becoming valuable intellectual property (IP) as many hours are invested in their training and optimization. Therefore, attackers may be interested in copying, reverse…

Cryptography and Security · Computer Science 2022-04-04 Mahdieh Grailoo , Zain Ul Abideen , Mairo Leier , Samuel Pagliarini

Natural language processing (NLP) models may leak private information in different ways, including membership inference, reconstruction or attribute inference attacks. Sensitive information may not be explicit in the text, but hidden in…

Computation and Language · Computer Science 2024-07-01 Pedro Faustini , Shakila Mahjabin Tonni , Annabelle McIver , Qiongkai Xu , Mark Dras

Over the past decade, the machine learning security community has developed a myriad of defenses for evasion attacks. An understudied question in that community is: for whom do these defenses defend? This work considers common approaches to…

Machine Learning · Computer Science 2023-08-24 Luke E. Richards , Edward Raff , Cynthia Matuszek

Recent developments in deep learning have led to great success in various natural language processing (NLP) tasks. However, these applications may involve data that contain sensitive information. Therefore, how to achieve good performance…

Computation and Language · Computer Science 2023-10-24 Lijie Hu , Ivan Habernal , Lei Shen , Di Wang
‹ Prev 1 3 4 5 6 7 10 Next ›