Related papers: MetaBackdoor: Exploiting Positional Encoding as a …
Large visual language models (LVLMs) have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contaminated data. Existing backdoor defense techniques are usually…
Multimodal Large Language Models (MLLMs) have showcased impressive performance in a variety of multimodal tasks. On the other hand, the integration of additional image modality may allow the malicious users to inject harmful content inside…
Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word…
Large language models (LLMs) can sometimes report the strategies they actually use to solve tasks, yet at other times seem unable to recognize those strategies that govern their behavior. This suggests a limited degree of metacognition -…
The emergence of graph foundation models (GFMs), particularly those incorporating language models (LMs), has revolutionized graph learning and demonstrated remarkable performance on text-attributed graphs (TAGs). However, compared to…
Large language model (LLM) unlearning has become a critical mechanism for removing undesired data, knowledge, or behaviors from pre-trained models while retaining their general utility. Yet, with the rise of open-weight LLMs, we ask: can…
In-context learning (ICL) has emerged as a powerful paradigm leveraging LLMs for specific downstream tasks by utilizing labeled examples as demonstrations (demos) in the preconditioned prompts. Despite its promising performance, crafted…
Large Language Models (LLMs) have demonstrated remarkable capabilities in performing tasks across various domains without needing explicit retraining. This capability, known as In-Context Learning (ICL), while impressive, exposes LLMs to a…
Backdoor mechanisms have traditionally been studied as security threats that compromise the integrity of machine learning models. However, the same mechanism -- the conditional activation of specific behaviors through input triggers -- can…
The integration of additional modalities increases the susceptibility of large vision-language models (LVLMs) to safety risks, such as jailbreak attacks, compared to their language-only counterparts. While existing research primarily…
While Large Language Models (LLMs) have shown significant advancements in performance, various jailbreak attacks have posed growing safety and ethical risks. Malicious users often exploit adversarial context to deceive LLMs, prompting them…
This paper studies the integration off Large Language Models into cybersecurity tools and protocols. The main issue discussed in this paper is how traditional rule-based and signature based security systems are not enough to deal with…
The security of Large Language Model (LLM) applications is fundamentally challenged by "form-first" attacks like prompt injection and jailbreaking, where malicious instructions are embedded within user inputs. Conventional defenses, which…
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…
The proliferation of Large Language Models (LLMs) has introduced critical security challenges, where adversarial actors can manipulate input prompts to cause significant harm and circumvent safety alignments. These prompt-based attacks…
Tool-use large language model (LLM) agents are increasingly deployed to support sensitive workflows, relying on tool calls for retrieval, external API access, and session memory management. While prior research has examined various threats,…
Backdoor attacks creating 'sleeper agents' in large language models (LLMs) pose significant safety risks. This study employs mechanistic interpretability to explore resulting internal structural differences. Comparing clean Qwen2.5-3B…
Machine learning systems are vulnerable to backdoor attacks, where attackers manipulate model behavior through data tampering or architectural modifications. Traditional backdoor attacks involve injecting malicious samples with specific…
Large Language Models (LLMs) remain vulnerable to jailbreak attacks that bypass their safety mechanisms. Existing attack methods are fixed or specifically tailored for certain models and cannot flexibly adjust attack strength, which is…
Despite recent advances, Large Language Models remain vulnerable to jailbreak attacks that bypass alignment safeguards and elicit harmful outputs. While prior research has proposed various attack strategies differing in human readability…