Related papers: Obfuscated Activations Bypass LLM Latent-Space Def…
Fine-tuning has emerged as a critical process in leveraging Large Language Models (LLMs) for specific downstream tasks, enabling these models to achieve state-of-the-art performance across various domains. However, the fine-tuning process…
The increasing use of Artificial Intelligence (AI) technologies, such as Large Language Models (LLMs) has led to nontrivial improvements in various tasks, including accurate authorship identification of documents. However, while LLMs…
Deep learning is becoming increasingly popular in real-life applications, especially in natural language processing (NLP). Users often choose training outsourcing or adopt third-party data and models due to data and computation resources…
Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs. However, such access may also let malicious actors undermine model safety. To demonstrate the challenge of defending finetuning…
Harmful fine-tuning attacks pose a major threat to the security of large language models (LLMs), allowing adversaries to compromise safety guardrails with minimal harmful data. While existing defenses attempt to reinforce LLM alignment,…
Despite extensive alignment efforts, Large Vision-Language Models (LVLMs) remain vulnerable to jailbreak attacks. To mitigate these risks, existing detection methods are essential, yet they face two major challenges: generalization and…
Embodied Large Language Models (LLMs) enable AI agents to interact with the physical world through natural language instructions and actions. However, beyond the language-level risks inherent to LLMs themselves, embodied LLMs with…
Backdoor attacks pose a critical threat by embedding hidden triggers into inputs, causing models to misclassify them into target labels. While extensive research has focused on mitigating these attacks in object recognition models through…
LLMs increasingly exhibit over-refusal behavior, where safety mechanisms cause models to reject benign instructions that seemingly resemble harmful content. This phenomenon diminishes utility in production applications that repeatedly rely…
With the enhanced performance of large models on natural language processing tasks, potential moral and ethical issues of large models arise. There exist malicious attackers who induce large models to jailbreak and generate information…
Effective detection of energy theft can prevent revenue losses of utility companies and is also important for smart grid security. In recent years, enabled by the massive fine-grained smart meter data, deep learning (DL) approaches are…
Deep convolutional neural networks are susceptible to adversarial attacks. They can be easily deceived to give an incorrect output by adding a tiny perturbation to the input. This presents a great challenge in making CNNs robust against…
Large Language Models (LLMs) rely on safety alignment to produce socially acceptable responses. However, this behavior is known to be brittle: further fine-tuning, even on benign or lightly contaminated data, can degrade safety and…
Large language models (LLMs) are vulnerable to adversarial attacks that can elicit harmful responses. Defending against such attacks remains challenging due to the opacity of jailbreaking mechanisms and the high computational cost of…
Large language models (LLMs) have demonstrated immense utility across various industries. However, as LLMs advance, the risk of harmful outputs increases due to incorrect or malicious instruction prompts. While current methods effectively…
Training against white-box deception detectors has been proposed as a way to make AI systems honest. However, such training risks models learning to obfuscate their deception to evade the detector. Prior work has studied obfuscation only in…
Can large language models introspect, that is, accurately detect perturbations to their own internal states? We systematically investigate this question using activation steering in Meta-Llama-3.1-8B-Instruct. First, we show that the binary…
As Large Language Models (LLMs) increasingly become key components in various AI applications, understanding their security vulnerabilities and the effectiveness of defense mechanisms is crucial. This survey examines the security challenges…
Deep Neural Networks (DNNs) have become a powerful toolfor a wide range of problems. Yet recent work has found an increasing variety of adversarial samplesthat can fool them. Most existing detection mechanisms against adversarial…
LLMs are increasingly capable of persuasion, which raises the question of how to protect users against manipulation. In a preregistered user study (N=120) across four decision-making scenarios, we find that an adversarial LLM with a hidden…