Related papers: Before the Last Token: Diagnosing Final-Token Safe…
Text-to-image generative models are widely deployed in creative tools and online platforms. To mitigate misuse, these systems rely on safety filters and moderation pipelines that aim to block harmful or policy violating content. In this…
Most commonly used language models (LMs) are instruction-tuned and aligned using a combination of fine-tuning and reinforcement learning, causing them to refuse users requests deemed harmful by the model. However, jailbreak prompts can…
Multimodal Large Language Models (MLLMs) extend text-only LLMs with visual reasoning, but also introduce new safety failure modes under visually grounded instructions. We study comic-template jailbreaks that embed harmful goals inside…
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…
Jailbreak prompts pose a significant threat in AI and cybersecurity, as they are crafted to bypass ethical safeguards in large language models, potentially enabling misuse by cybercriminals. This paper analyzes jailbreak prompts from a…
In the past few years, Language Models (LMs) have shown par-human capabilities in several domains. Despite their practical applications and exceeding user consumption, they are susceptible to jailbreaks when malicious input exploits the…
This study reveals a critical safety blind spot in modern LLMs: learning-style queries, which closely resemble ordinary educational questions, can reliably elicit harmful responses. The learning-style queries are constructed by a novel…
Machine learning is advancing rapidly, with applications bringing notable benefits, such as improvements in translation and code generation. Models like ChatGPT, powered by Large Language Models (LLMs), are increasingly integrated into…
As Vision-Language Models (VLMs) demonstrate increasing capabilities across real-world applications such as code generation and chatbot assistance, ensuring their safety has become paramount. Unlike traditional Large Language Models (LLMs),…
We discover a novel and surprising phenomenon of unintentional misalignment in reasoning language models (RLMs), which we call self-jailbreaking. Specifically, after benign reasoning training on math or code domains, RLMs will use multiple…
Recent work has shown that the hidden states of large language models contain signals useful for uncertainty estimation and hallucination detection, motivating a growing interest in efficient probe-based approaches. Yet it remains unclear…
Safety-aligned Large Language Models (LLMs) still show two dominant failure modes: they are easily jailbroken, or they over-refuse harmless inputs that contain sensitive surface signals. We trace both to a common cause: current models…
Existing invasive (backdoor) fingerprints suffer from high-perplexity triggers that are easily filtered, fixed response patterns exposed by heuristic detectors, and spurious activations on benign inputs. We introduce \textsc{ForgetMark}, a…
With the rapid advancement of large language models (LLMs), ensuring their safe use becomes increasingly critical. Fine-tuning is a widely used method for adapting models to downstream tasks, yet it is vulnerable to jailbreak attacks.…
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-training stage,…
Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…
Large Language Models (LLMs) are powerful text generators, yet they can produce toxic or harmful content even when given seemingly harmless prompts. This presents a serious safety challenge and can cause real-world harm. Toxicity is often…
Recently, prompt tuning \cite{lester2021power} has gradually become a new paradigm for NLP, which only depends on the representation of the words by freezing the parameters of pre-trained language models (PLMs) to obtain remarkable…
Public LLMs such as the Llama 2-Chat underwent alignment training and were considered safe. Recently Qi et al. [2024] reported that even benign fine-tuning on seemingly safe datasets can give rise to unsafe behaviors in the models. The…
Finetuning pretrained large language models (LLMs) has become the standard paradigm for developing downstream applications. However, its security implications remain unclear, particularly regarding whether finetuned LLMs inherit jailbreak…