Related papers: Can Editing LLMs Inject Harm?
Large language models (LLMs) remain vulnerable to jailbreaking attacks despite their impressive capabilities. Investigating these weaknesses is crucial for robust safety mechanisms. Existing attacks primarily distract LLMs by introducing…
In-context knowledge editing (IKE) enables efficient modification of large language model (LLM) outputs without parameter changes and at zero-cost. However, it can be misused to manipulate responses opaquely, e.g., insert misinformation or…
Current research in adversarial robustness of LLMs focuses on discrete input manipulations in the natural language space, which can be directly transferred to closed-source models. However, this approach neglects the steady progression of…
With the rapid development of Large Language Models (LLMs), numerous mature applications of LLMs have emerged in the field of content safety detection. However, we have found that LLMs exhibit blind trust in safety detection agents. The…
Large language models are aligned to be safe, preventing users from generating harmful content like misinformation or instructions for illegal activities. However, previous work has shown that the alignment process is vulnerable to…
We introduce Advertisement Embedding Attacks (AEA), a new class of LLM security threats that stealthily inject promotional or malicious content into model outputs and AI agents. AEA operate through two low-cost vectors: (1) hijacking…
Large language models (LLMs) have gained human trust due to their capabilities and helpfulness. However, this in turn may allow LLMs to affect users' mindsets by manipulating language. It is termed as gaslighting, a psychological effect. In…
While large language models (LLMs) present significant potential for supporting numerous real-world applications and delivering positive social impacts, they still face significant challenges in terms of the inherent risk of privacy…
Large language models (LLMs) store vast amounts of knowledge, which often requires updates to correct factual errors, incorporate newly acquired information, or adapt model behavior. Model editing methods have emerged as efficient solutions…
The integration of Large Language Models (LLMs) into healthcare applications offers promising advancements in medical diagnostics, treatment recommendations, and patient care. However, the susceptibility of LLMs to adversarial attacks poses…
Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…
Backdoor attacks are a kind of emergent security threat in deep learning. After being injected with a backdoor, a deep neural model will behave normally on standard inputs but give adversary-specified predictions once the input contains…
Large Language Models (LLMs) have demonstrated great capabilities in natural language understanding and generation, largely attributed to the intricate alignment process using human feedback. While alignment has become an essential training…
Prompt injection attack, where an attacker injects a prompt into the original one, aiming to make an Large Language Model (LLM) follow the injected prompt to perform an attacker-chosen task, represent a critical security threat. Existing…
With the advancement of technology, large language models (LLMs) have achieved remarkable performance across various natural language processing (NLP) tasks, powering LLM-integrated applications like Microsoft Copilot. However, as LLMs…
Large language models (LLMs) are often fine-tuned on uncurated text datasets that adversaries can poison. Existing poisoning attacks primarily rely on fixed trigger phrases that defenses such as outlier detection, clean-data regularization,…
Recent studies have revealed a security threat to natural language processing (NLP) models, called the Backdoor Attack. Victim models can maintain competitive performance on clean samples while behaving abnormally on samples with a specific…
Large Language Models (LLMs) have emerged as powerful tools, but their inherent safety risks - ranging from harmful content generation to broader societal harms - pose significant challenges. These risks can be amplified by the recent…
Merging Large Language Models (LLMs) is a cost-effective technique for combining multiple expert LLMs into a single versatile model, retaining the expertise of the original ones. However, current approaches often overlook the importance of…
Knowledge editing aims to change language models' performance on several special cases (i.e., editing scope) by infusing the corresponding expected knowledge into them. With the recent advancements in large language models (LLMs), knowledge…