English
Related papers

Related papers: Jailbreak-Tuning: Models Efficiently Learn Jailbre…

200 papers

Deep learning models are well known to be susceptible to backdoor attack, where the attacker only needs to provide a tampered dataset on which the triggers are injected. Models trained on the dataset will passively implant the backdoor, and…

Cryptography and Security · Computer Science 2024-06-21 Zonghao Ying , Bin Wu

Diffusion models are state-of-the-art deep learning empowered generative models that are trained based on the principle of learning forward and reverse diffusion processes via progressive noise-addition and denoising. To gain a better…

Computer Vision and Pattern Recognition · Computer Science 2023-06-12 Sheng-Yen Chou , Pin-Yu Chen , Tsung-Yi Ho

In recent years, the security vulnerabilities of Multi-modal Large Language Models (MLLMs) have become a serious concern in the Generative Artificial Intelligence (GenAI) research. These highly intelligent models, capable of performing…

Cryptography and Security · Computer Science 2026-01-12 Badhan Chandra Das , Md Tasnim Jawad , Joaquin Molto , M. Hadi Amini , Yanzhao Wu

Deep Neural Networks are well known to be vulnerable to adversarial attacks and backdoor attacks, where minor modifications on the input are able to mislead the models to give wrong results. Although defenses against adversarial attacks…

Machine Learning · Computer Science 2022-08-01 Kaidi Jin , Tianwei Zhang , Chao Shen , Yufei Chen , Ming Fan , Chenhao Lin , Ting Liu

Deep Neural Networks have recently gained lots of success after enabling several breakthroughs in notoriously challenging problems. Training these networks is computationally expensive and requires vast amounts of training data. Selling…

Machine Learning · Computer Science 2018-06-12 Yossi Adi , Carsten Baum , Moustapha Cisse , Benny Pinkas , Joseph Keshet

The increasing complexity of AI models, especially in deep learning, has raised concerns about transparency and accountability, particularly in high-stakes applications like medical diagnostics, where opaque models can undermine trust.…

Cryptography and Security · Computer Science 2024-11-26 Songning Lai , Yu Huang , Jiayu Yang , Gaoxiang Huang , Wenshuo Chen , Yutao Yue

Developers try to evaluate whether an AI system can be misused by adversaries before releasing it; for example, they might test whether a model enables cyberoffense, user manipulation, or bioterrorism. In this work, we show that…

Cryptography and Security · Computer Science 2024-07-03 Erik Jones , Anca Dragan , Jacob Steinhardt

The rise of conversational interfaces has greatly enhanced LLM usability by leveraging dialogue history for sophisticated reasoning. However, this reliance introduces an unexplored attack surface. This paper introduces Trojan Horse…

Artificial Intelligence · Computer Science 2025-07-08 Wei Duan , Li Qian

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

The incremental diffusion of machine learning algorithms in supporting cybersecurity is creating novel defensive opportunities but also new types of risks. Multiple researches have shown that machine learning methods are vulnerable to…

Cryptography and Security · Computer Science 2021-06-18 Giovanni Apruzzese , Mauro Andreolini , Luca Ferretti , Mirco Marchetti , Michele Colajanni

In recent years, the rapid development of large language models (LLMs) has achieved remarkable performance across various tasks. However, research indicates that LLMs are vulnerable to jailbreak attacks, where adversaries can induce the…

Cryptography and Security · Computer Science 2024-08-23 Jiawei Zhao , Kejiang Chen , Xiaojian Yuan , Weiming Zhang

The demand of customized large language models (LLMs) has led to commercial LLMs offering black-box fine-tuning APIs, yet this convenience introduces a critical security loophole: attackers could jailbreak the LLMs by fine-tuning them with…

Cryptography and Security · Computer Science 2026-01-21 Zhixin Xie , Xurui Song , Jun Luo

Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…

Machine Learning · Computer Science 2024-08-22 Samyak Jain , Ekdeep Singh Lubana , Kemal Oksuz , Tom Joy , Philip H. S. Torr , Amartya Sanyal , Puneet K. Dokania

Backdoor attacks allow an attacker to embed a specific vulnerability in a machine learning algorithm, activated when an attacker-chosen pattern is presented, causing a specific misprediction. The need to identify backdoors in biometric…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Alexander Unnervik , Hatef Otroshi Shahreza , Anjith George , Sébastien Marcel

Federated learning enables thousands of participants to construct a deep learning model without sharing their private training data with each other. For example, multiple smartphones can jointly train a next-word predictor for keyboards…

Cryptography and Security · Computer Science 2019-08-07 Eugene Bagdasaryan , Andreas Veit , Yiqing Hua , Deborah Estrin , Vitaly Shmatikov

As large language models (LLMs) grow more capable, they face growing vulnerability to sophisticated jailbreak attacks. While developers invest heavily in alignment finetuning and safety guardrails, researchers continue publishing novel…

Cryptography and Security · Computer Science 2025-08-14 Boyuan Chen , Minghao Shao , Abdul Basit , Siddharth Garg , Muhammad Shafique

Federated Learning (FL) allows multiple clients to collaboratively train a Neural Network (NN) model on their private data without revealing the data. Recently, several targeted poisoning attacks against FL have been introduced. These…

Cryptography and Security · Computer Science 2022-01-04 Phillip Rieger , Thien Duc Nguyen , Markus Miettinen , Ahmad-Reza Sadeghi

As large language models (LLMs) advance, ensuring AI safety and alignment is paramount. One popular approach is prompt guards, lightweight mechanisms designed to filter malicious queries while being easy to implement and update. In this…

Machine Learning · Computer Science 2025-10-08 Jaiden Fairoze , Sanjam Garg , Keewoo Lee , Mingyuan Wang

Deep neural networks have proven to be quite effective in a wide variety of machine learning tasks, ranging from improved speech recognition systems to advancing the development of autonomous vehicles. However, despite their superior…

Machine Learning · Computer Science 2016-12-14 Qinglong Wang , Wenbo Guo , Alexander G. Ororbia , Xinyu Xing , Lin Lin , C. Lee Giles , Xue Liu , Peng Liu , Gang Xiong

Model stealing, i.e., unauthorized access and exfiltration of deep learning models, has become one of the major threats. Proprietary models may be protected by access controls and encryption. However, in reality, these measures can be…

Cryptography and Security · Computer Science 2024-05-27 Yuling Cai , Fan Xiang , Guozhu Meng , Yinzhi Cao , Kai Chen