Related papers: Harnessing Hyperbolic Geometry for Harmful Prompt …

Large Vision-Language Models (LVLMs) have demonstrated their powerful multimodal capabilities. However, they also face serious safety problems, as adversaries can induce robustness issues in LVLMs through the use of well-designed…

Detecting illicit visual content demands more than image-level NSFW flags; moderators must also know what objects make an image illegal and where those objects occur. We introduce a zero-shot pipeline that simultaneously (i) detects if an…

Hateful memes are widespread in social media and convey negative information. The main challenge of hateful memes detection is that the expressive meaning can not be well recognized by a single modality. In order to further integrate modal…

Current Vision Language Models (VLMs) remain vulnerable to malicious prompts that induce harmful outputs. Existing safety benchmarks for VLMs primarily rely on automated evaluation methods, but these methods struggle to detect implicit…

Safeguarding vision-language models (VLMs) is a critical challenge, as existing methods often suffer from over-defense, which harms utility, or rely on shallow alignment, failing to detect complex threats that require deep reasoning. To…

Large language models (LLMs) excel in diverse applications but face dual challenges: generating harmful content under jailbreak attacks and over-refusal of benign queries due to rigid safety mechanisms. These issues are further complicated…

With the rapid advancement of multimodal learning, pre-trained Vision-Language Models (VLMs) such as CLIP have demonstrated remarkable capacities in bridging the gap between visual and language modalities. However, these models remain…

Adversarial prompts are capable of jailbreaking frontier large language models (LLMs) and inducing undesirable behaviours, posing a significant obstacle to their safe deployment. Current mitigation strategies primarily rely on activating…

Large Vision-Language Models (LVLMs) unlock powerful multimodal reasoning but also expand the attack surface, particularly through adversarial inputs that conceal harmful goals in benign prompts. We propose SHIELD, a lightweight,…

In the realm of large vision language models (LVLMs), jailbreak attacks serve as a red-teaming approach to bypass guardrails and uncover safety implications. Existing jailbreaks predominantly focus on the visual modality, perturbing solely…

Large Vision-Language Models (LVLMs) have achieved impressive progress across various applications but remain vulnerable to malicious queries that exploit the visual modality. Existing alignment approaches typically fail to resist malicious…

Memes often merge visuals with brief text to share humor or opinions, yet some memes contain harmful messages such as hate speech. In this paper, we introduces MemeBLIP2, a light weight multimodal system that detects harmful memes by…

Implicit hate speech (IHS) is indirect language that conveys prejudice or hatred through subtle cues, sarcasm or coded terminology. IHS is challenging to detect as it does not include explicit derogatory or inflammatory words. To address…

Despite their capabilities, Large Language Models (LLMs) remain opaque with limited understanding of their internal representations. Current interpretability methods either focus on input-oriented feature extraction, such as supervised…

Large Language Models (LLMs) have attracted significant attention in recommender systems for their excellent world knowledge capabilities. However, existing methods that rely on Euclidean space struggle to capture the rich hierarchical…

Prompt-based verification is widely used to mitigate hallucinations in large vision-language models (LVLMs), yet when it helps remains poorly understood. We systematically study verification prompting across two representative LVLM…

LLM-based programming assistants offer the promise of programming faster but with the risk of introducing more security vulnerabilities. Prior work has studied how LLMs could be maliciously fine-tuned to suggest vulnerabilities more often.…

Hateful meme detection is a challenging multimodal task that requires comprehension of both vision and language, as well as cross-modal interactions. Recent studies have tried to fine-tune pre-trained vision-language models (PVLMs) for this…

The rapid expansion of social media leads to a marked increase in hate speech, which threatens personal lives and results in numerous hate crimes. Detecting hate speech presents several challenges: diverse dialects, frequent code-mixing,…

Weakly-Supervised Semantic Segmentation (WSSS) aims to train segmentation models using image data with only image-level supervision. Since precise pixel-level annotations are not accessible, existing methods typically focus on producing…