Related papers: Steering Without Side Effects: Improving Post-Depl…
Automated unit test generation using large language models (LLMs) holds great promise but often struggles with generating tests that are both correct and maintainable in real-world projects. This paper presents KTester, a novel framework…
We introduce Tempest, a multi-turn adversarial framework that models the gradual erosion of Large Language Model (LLM) safety through a tree search perspective. Unlike single-turn jailbreaks that rely on one meticulously engineered prompt,…
The static ``train then deploy" paradigm fundamentally limits Large Language Models (LLMs) from dynamically adapting their weights in response to continuous streams of new information inherent in real-world tasks. Test-Time Training (TTT)…
LLMs have shown remarkable capabilities, but precisely controlling their response behavior remains challenging. Existing activation steering methods alter LLM behavior indiscriminately, limiting their practical applicability in settings…
As large language models (LLMs) become easily accessible nowadays, the trade-off between safety and helpfulness can significantly impact user experience. A model that prioritizes safety will cause users to feel less engaged and assisted…
Vision Language Models (VLMs) have demonstrated impressive capabilities in integrating visual and textual information for understanding and reasoning, but remain highly vulnerable to adversarial attacks. While activation steering has…
The proliferation of jailbreak attacks against large language models (LLMs) highlights the need for robust security measures. However, in multi-round dialogues, malicious intentions may be hidden in interactions, leading LLMs to be more…
Jailbreak attacks pose a serious threat to Large Language Models (LLMs) by bypassing their safety mechanisms. A truly advanced jailbreak is defined not only by its effectiveness but, more critically, by its stealthiness. However, existing…
In recent years, the rapid development of large language models (LLMs) has achieved remarkable performance across various tasks. However, research indicates that LLMs are vulnerable to jailbreak attacks, where adversaries can induce the…
In reasoning tasks, even a minor error can cascade into inaccurate results, leading to suboptimal performance of large language models in such domains. Earlier fine-tuning approaches sought to mitigate this by leveraging more precise…
Large Multi-Modal Models (LMMs) have demonstrated impressive capabilities as general-purpose chatbots able to engage in conversations about visual inputs. However, their responses are influenced by societal biases present in their training…
Large Language Models (LLMs) have revolutionized artificial intelligence, demonstrating remarkable computational power and linguistic capabilities. However, these models are inherently prone to various biases stemming from their training…
Red-teaming has been a widely adopted way to evaluate the harmfulness of Large Language Models (LLMs). It aims to jailbreak a model's safety behavior to make it act as a helpful agent disregarding the harmfulness of the query. Existing…
Large Language Models (LLMs) are increasingly deployed in settings where Chain-of-Thought (CoT) is interpreted by users. This creates a new safety risk: attackers may manipulate the model's observable CoT to make malicious behaviors. In…
Steering large language models (LLMs) is usually done by either instruction prompting or activation steering. Prompting often gives strong control, but caches guidance tokens at every layer and can clutter long interactions; activation…
Large Language Models (LLMs) face prominent security risks from jailbreaking, a practice that manipulates models to bypass built-in security constraints and generate unethical or unsafe content. Among various jailbreak techniques,…
This work introduces SteerVLM, a lightweight steering module designed to guide Vision-Language Models (VLMs) towards outputs that better adhere to desired instructions. Our approach learns from the latent embeddings of paired prompts…
While language models have shown remarkable performance across diverse tasks, they still encounter challenges in complex reasoning scenarios. Recent research suggests that language models trained on linearized search traces toward…
As Large Language Models (LLMs) gain traction across critical domains, ensuring secure and trustworthy training processes has become a major concern. Backdoor attacks, where malicious actors inject hidden triggers into training data, are…
Speech Language Models (SLMs) enable natural interactions via spoken instructions, which more effectively capture user intent by detecting nuances in speech. The richer speech signal introduces new security risks compared to text-based…