相关论文: Vision-LLMs Can Fool Themselves with Self-Generate…

In recent years, the emergence of models capable of generating images from text has attracted considerable interest, offering the possibility of creating realistic images from text descriptions. Yet these advances have also raised concerns…

Large language models (LLMs) have shown promise in robotic procedural planning, yet their human-centric reasoning often omits the low-level, grounded details needed for robotic execution. Vision-language models (VLMs) offer a path toward…

Reliable prediction by classifiers is crucial for their deployment in high security and dynamically changing situations. However, modern neural networks often exhibit overconfidence for misclassified predictions, highlighting the need for…

As large language models (LLMs) become an important way of information access, there have been increasing concerns that LLMs may intensify the spread of unethical content, including implicit bias that hurts certain populations without…

With social media growth, users employ stylistic fonts and font-like emoji to express individuality, creating visually appealing text that remains human-readable. However, these fonts introduce hidden vulnerabilities in NLP models: while…

While large language models with vision capabilities (VLMs), e.g., GPT-4o and Gemini 1.5 Pro, score high on many vision-understanding benchmarks, they are still struggling with low-level vision tasks that are easy to humans. Specifically,…

One way to mitigate risks in vision-language models (VLMs) is to remove dangerous samples in their training data. However, such data moderation can be easily bypassed when harmful images are split into small, benign-looking patches,…

Vision-Language Models (VLMs) excel at visual understanding but often suffer from visual hallucinations, where they generate descriptions of nonexistent objects, actions, or concepts, posing significant risks in safety-critical…

While Vision-Language Models (VLMs) have shown remarkable abilities in visual and language reasoning tasks, they invariably generate flawed responses. Self-correction that instructs models to refine their outputs presents a promising…

Large Language Models (LLMs) excel in processing and generating human language, powered by their ability to interpret and follow instructions. However, their capabilities can be exploited through prompt injection attacks. These attacks…

Large Language Models (LLMs) are swiftly advancing in architecture and capability, and as they integrate more deeply into complex systems, the urgency to scrutinize their security properties grows. This paper surveys research in the…

Large Language Models (LLMs) are known to be vulnerable to backdoor attacks, where triggers embedded in poisoned samples can maliciously alter LLMs' behaviors. In this paper, we move beyond attacking LLMs and instead examine backdoor…

Many vision-language models (VLMs) that prove very effective at a range of multimodal task, build on CLIP-based vision encoders, which are known to have various limitations. We investigate the hypothesis that the strong language backbone in…

Recently, the powerful large language models (LLMs) have been instrumental in propelling the progress of recommender systems (RS). However, while these systems have flourished, their susceptibility to security threats has been largely…

Large Language Models (LLMs) are effective at deceiving, when prompted to do so. But under what conditions do they deceive spontaneously? Models that demonstrate better performance on reasoning tasks are also better at prompted deception.…

Foundation models that bridge vision and language have made significant progress. While they have inspired many life-enriching applications, their potential for abuse in creating new threats remains largely unexplored. In this paper, we…

Visualizations help communicate data insights, but deceptive data representations can distort their interpretation and propagate misinformation. While recent Vision Language Models (VLMs) perform well on many chart understanding tasks,…

Large Language Models (LLMs) demonstrate impressive capabilities across various fields, yet their increasing use raises critical security concerns. This article reviews recent literature addressing key issues in LLM security, with a focus…

Humans perform visual perception at multiple levels, including low-level object recognition and high-level semantic interpretation such as behavior understanding. Subtle differences in low-level details can lead to substantial changes in…

Large Vision Language Models (LVLMs) achieve strong multimodal reasoning but frequently exhibit hallucinations and incorrect responses with high certainty, which hinders their usage in high-stakes domains. Existing verbalized confidence…