paper-with-me

홈 › Papers

Universal and Context-Independent Triggers for Precise Control of LLM Outputs

2024-11-22 · Jiashuo Liang, Guancheng Li, Yang Yu

Large language models (LLMs) have been widely adopted in applications such as automated content generation and even critical decision-making systems. However, the risk of prompt injection allows for potential manipulation of LLM outputs. While numerous attack methods have been documented, achieving full control over these outputs remains challenging, often requiring experienced attackers to make multiple attempts and depending heavily on the prompt context. Recent advancements in gradient-based white-box attack techniques have shown promise in tasks like jailbreaks and system prompt leaks. Our research generalizes gradient-based attacks to find a trigger that is (1) Universal: effective irrespective of the target output; (2) Context-Independent: robust across diverse prompt contexts; and (3) Precise Output: capable of manipulating LLM inputs to yield any specified output with high accuracy. We propose a novel method to efficiently discover such triggers and assess the effectiveness of the proposed attack. Furthermore, we discuss the substantial threats posed by such attacks to LLM-based applications, highlighting the potential for adversaries to taking over the decisions and actions made by AI agents.

📄 PDF Abstract BibTeX arXiv:2411.14738

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Making

Similar Papers 제목 키워드 기반

Exploring the Universal Vulnerability of Prompt-based Learning Paradigm

2022-04-11 · Findings (NAACL) 2022 7 · Lei Xu, Yangyi Chen, Ganqu Cui, Hongcheng Gao 외

Prompt-based learning paradigm bridges the gap between pre-training and fine-tuning, and works effectively under the few-shot setting. However, we find that this learning paradigm inherits the vulnerability from the pre-…

Exploring the Universal Vulnerability of Prompt-based Learning Paradigm

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Prompt-based learning paradigm bridges the gap between pre-training and fine-tuning, and works effectively under the few-shot setting. However, we find that this learning paradigm inherits the vulnerability from the pre-…

Universal Backdoor Attacks

2023-11-30 · Benjamin Schneider, Nils Lukas, Florian Kerschbaum

Web-scraped datasets are vulnerable to data poisoning, which can be used for backdooring deep image classifiers during training. Since training on large datasets is expensive, a model is trained once and re-used many tim…

Data Poisoning

BadActs: A Universal Backdoor Defense in the Activation Space

2024-05-18 · Biao Yi, Sishuo Chen, Yiming Li, Tong Li 외

Backdoor attacks pose an increasingly severe security threat to Deep Neural Networks (DNNs) during their development stage. In response, backdoor sample purification has emerged as a promising defense mechanism, aiming t…

backdoor defense

Universal Adversarial Triggers for Attacking and Analyzing NLP

2019-08-20 · IJCNLP 2019 11 · Eric Wallace, Shi Feng, Nikhil Kandpal, Matt Gardner 외

Adversarial examples highlight model vulnerabilities and are useful for evaluation and interpretation. We define universal adversarial triggers: input-agnostic sequences of tokens that trigger a model to produce a specif…

Language ModelingLanguage ModellingReading Comprehension