LLM Security

Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition

Authors: Edoardo Debenedetti, Javier Rando, Daniel Paleka, Silaghi Fineas Florin, Dragos Albastroiu, Niv Cohen, Yuval Lemberg, Reshmi Ghosh, Rui Wen, Ahmed Salem, Giovanni Cherubin, Santiago Zanella-Beguelin, Robin Schmid, Victor Klemm, Takahiro Miki, Chenhao Li, Stefan Kraft, Mario Fritz, Florian Tramèr, Sahar Abdelnabi, Lea Schönherr | Published: 2024-06-12
LLM Security
Prompt Injection
Defense Method
2024.06.12 2025.05.27
Literature Database

A Study of Backdoors in Instruction Fine-tuned Language Models

Authors: Jayaram Raghuram, George Kesidis, David J. Miller | Published: 2024-06-12 | Updated: 2024-08-21
LLM Security
Backdoor Attack
Defense Method
2024.06.12 2025.05.27
Literature Database

Knowledge Return Oriented Prompting (KROP)

Authors: Jason Martin, Kenneth Yeung | Published: 2024-06-11
LLM Security
Prompt Injection
Attack Method
2024.06.11 2025.05.27
Literature Database

A Survey of Recent Backdoor Attacks and Defenses in Large Language Models

Authors: Shuai Zhao, Meihuizi Jia, Zhongliang Guo, Leilei Gan, Xiaoyu Xu, Xiaobao Wu, Jie Fu, Yichao Feng, Fengjun Pan, Luu Anh Tuan | Published: 2024-06-10 | Updated: 2025-01-04
LLM Security
Backdoor Attack
2024.06.10 2025.05.27
Literature Database

An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection

Authors: Shenao Yan, Shen Wang, Yue Duan, Hanbin Hong, Kiho Lee, Doowon Kim, Yuan Hong | Published: 2024-06-10
LLM Security
Backdoor Attack
Prompt Injection
2024.06.10 2025.05.27
Literature Database

LLM Dataset Inference: Did you train on my dataset?

Authors: Pratyush Maini, Hengrui Jia, Nicolas Papernot, Adam Dziedzic | Published: 2024-06-10
LLM Security
Data Privacy Assessment
Membership Inference
2024.06.10 2025.05.27
Literature Database

Safety Alignment Should Be Made More Than Just a Few Tokens Deep

Authors: Xiangyu Qi, Ashwinee Panda, Kaifeng Lyu, Xiao Ma, Subhrajit Roy, Ahmad Beirami, Prateek Mittal, Peter Henderson | Published: 2024-06-10
LLM Security
Prompt Injection
Safety Alignment
2024.06.10 2025.05.27
Literature Database

How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States

Authors: Zhenhong Zhou, Haiyang Yu, Xinghua Zhang, Rongwu Xu, Fei Huang, Yongbin Li | Published: 2024-06-09 | Updated: 2024-06-13
LLM Security
Prompt Injection
Compliance with Ethical Guidelines
2024.06.09 2025.05.27
Literature Database

Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs

Authors: Fan Liu, Zhao Xu, Hao Liu | Published: 2024-06-07
LLM Security
Prompt Injection
Adversarial Training
2024.06.07 2025.05.27
Literature Database

BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents

Authors: Yifei Wang, Dizhan Xue, Shengjie Zhang, Shengsheng Qian | Published: 2024-06-05
LLM Security
Backdoor Attack
Prompt Injection
2024.06.05 2025.05.27
Literature Database
Next page