35 accepted papers
Generative models have demonstrated significant results in ultra-low bitrate image compression, owing to their powerful capabilities for content generation and texture completion. Existing works primarily based on diffusion models still face challenges such as limited bitrate adaptability and high c…
Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information. However, this also introduces a new threat surface: unreliable search results can mislead agents into producing unsafe outputs. Real-world incidents and our two in-the-wild observations show …
Safety alignment in large language models is typically evaluated under isolated queries, yet real-world use is inherently multi-turn. Although multi-turn jailbreaks are empirically effective, the structure of conversational safety failure remains insufficiently understood. In this work, we study saf…
Reinforcement learning (RL) has shown strong potential for enhancing reasoning in multimodal large language models (MLLMs), yet existing video reasoning methods often rely on coarse sequence-level rewards or single-factor token selection. Such approaches neglect fine-grained links among visual input…
Large Language Models (LLMs) have been augmented with web search to overcome the limitations of the static knowledge boundary by accessing up-to-date information from the open Internet. While this integration enhances model capability, it also introduces a distinct safety threat surface: the retriev…
Emojis are globally used non-verbal cues in digital communication, and extensive research has examined how large language models (LLMs) understand and utilize emojis across contexts. While usually associated with friendliness or playfulness, it is observed that emojis may trigger toxic content gener
Large language models (LLMs) can output sensitive information, which has emerged as a novel safety concern. Previous works focus on structured sensitive information (e.g. personal identifiable information). However, we notice that sensitive information can also be at semantic level, i.e. semantic s…
Auto-regressive large language models (LLMs) have yielded impressive performance in many real-world tasks. However, the new paradigm of these LLMs also exposes novel threats. In this paper, we explore their vulnerability to inference cost attacks, where a malicious user crafts Engorgio prompts to…
Vision Language Model (VLM) Agents are stateful, autonomous entities capable of perceiving and interacting with their environments through vision and language. Multi-agent systems comprise specialized agents who collaborate to solve a (complex) task. A core security property is **robustness**, stat…
Detecting toxic content using language models is important but challenging. While large language models (LLMs) have demonstrated strong performance in understanding Chinese, recent studies show that simple character substitutions in toxic Chinese text can easily confuse the state-of-the-art (SOTA) L…
We present MaskWM, a simple, efficient, and flexible framework for image watermarking. MaskWM has two variants: (1) MaskWM-D, which supports global watermark embedding, watermark localization, and local watermark extraction for applications such as tamper detection; (2) MaskWM-ED, which focuses on l…
Multimodal large language models(MLLMs) have demonstrated promising spatial understanding capabilities, such as referencing and grounding object descriptions. Despite their successes, MLLMs still fall short in fine-grained spatial perception abilities, such as generating detailed region descriptions…
Tokens are basic elements in the datasets for LLM training. It is well-known that many tokens representing Chinese phrases in the vocabulary of GPT (4o/4o-mini/o1/o3/4.5/4.1/o4-mini) are indicating contents like pornography or online gambling. Based on this observation, our goal is to locate Pollute
Intrinsic self-correction was initially proposed to improve LLMs’ responses via feedback solely based on their inherent capability. However, recent works show that LLMs’ intrinsic self-correction fails without oracle labels as feedback. In this paper, our research goal is to *interpret LLMs’ intrins…
In-orbit object detection is essential for Earth observation missions on satellites equipped with GPUs. A promising approach is to use pre-trained vision-language modeling (VLM) to enhance its open-vocabulary capability. However, adopting it on satellites poses two challenges: (1) satellite imagery…
Artificial Intelligence Generated Content (AIGC) has advanced significantly, particularly with the development of video generation models such as text-to-video (T2V) models and image-to-video (I2V) models. However, like other AIGC types, video generation requires robust content control. A common app…
Large Audio-Language Models (LALMs) are augmented with the ability to perceive audio, demonstrating impressive capabilities in processing combined audio and text signals. However, their reliability when faced with conflicting inputs across modalities remains largely unexplored. This study examines h
Large language models (LLMs) exhibit prompt leakage vulnerabilities, where they may be coaxed into revealing system prompts embedded in LLM services, raising intellectual property and confidentiality concerns. An intriguing question arises: Do LLMs genuinely internalize prompt leakage intents in the
"We present , a versatile multi-modal large language model (MLLM) with a joint mixing of model weights, visual embeddings and image scales. First, for stronger vision-language alignment, we unfreeze the large language model (LLM) during pre-training, and introduce a weight mix strategy between LLMs…
With the rapidly increasing number of satellites in space and their enhanced capabilities, the amount of earth observation images collected by satellites is exceeding the transmission limits of satellite-to-ground links. Although existing learned image compression solutions achieve remarkable perfor…
The risk of harmful contents generated by large language models (LLMs) becomes a critical concern. This paper systematically evaluates and enhances LLMs’ capability to perform course-correction, , the model can steer away from generating harmful content autonomously. First, we introduce the C2-Eval…
Inspired by the success of general-purpose models in NLP recent studies attempt to unify different vision tasks in the same sequence format and employ autoregressive Transformers for sequence prediction. They apply uni-directional attention to capture sequential dependencies and generate task sequen…
Model quantization is a compression technique that converts a full-precision model to a more compact low-precision version for better storage. Despite the great success of quantization, recent studies revealed the feasibility of malicious exploiting model quantization via implanting quantization-con…
Large language models (LLMs) encapsulate vast amounts of knowledge but still remain vulnerable to external misinformation. Existing research mainly studied this susceptibility behavior in a single-turn setting. However, belief can change during a multi-turn conversation, especially a persuasive one.…
The common toxicity and societal bias in contents generated by large language models (LLMs) necessitate strategies to reduce harm. Present solutions often demand white-box access to the model or substantial training, which is impractical for cutting-edge commercial LLMs. Moreover, prevailing prompti…
As one of the privacy threats to machine learning models, the membership inference attack (MIA) tries to infer whether a given sample is in the original training set of a victim model by analyzing its outputs. Recent studies only use the predicted hard labels to achieve impressive membership inferen…
Backdoor attacks against deep learning have been widely studied. Various attack techniques have been proposed for different domains and paradigms, e.g., image, point cloud, natural language processing, transfer learning, etc. These works normally adopt the data poisoning strategy to embed the backdo…
Model extraction attacks are proven to be a severe privacy threat to Machine Learning as a Service (MLaaS). A variety of techniques have been designed to steal a remote machine learning model with high accuracy and fidelity. However, how to extract a robust model with similar resilience against adve…
Monocular 3D object detection has long been a challenging task in autonomous driving. Most existing methods follow conventional 2D detectors to first localize object centers, and then predict 3D attributes by neighboring features. However, only using local visual features is insufficient to understa…
Deep neural networks (DNNs) are widely deployed on real-world devices. Concerns regarding their security have gained great attention from researchers. Recently, a new weight modification attack called bit flip attack (BFA) was proposed, which exploits memory fault inject techniques such as row hamme…
Semantic Role Labeling (SRL) aims at recognizing the predicate-argument structure of a sentence and can be decomposed into two subtasks: predicate disambiguation and argument labeling. Prior work deals with these two tasks independently, which ignores the semantic connection between the two tasks. I…
"3D point cloud classification models based on deep neural networks were proven to be vulnerable to adversarial examples, with a quantity of novel attack techniques proposed by researchers recently. It is of paramount importance to preserve the robustness of 3D models under adversarial environments,…
Watermarking has become the tendency in protecting the intellectual property of DNN models. Recent works, from the adversary's perspective, attempted to subvert watermarking mechanisms by designing watermark removal attacks. However, these attacks mainly adopted sophisticated fine-tuning techniques,…
Collaborative learning has gained great popularity due to its benefit of data privacy protection: participants can jointly train a Deep Learning model without sharing their training sets. However, recent works discovered that an adversary can fully recover the sensitive training samples from the sha…
Dense object detectors rely on the sliding-window paradigm that predicts the object over a regular grid of image. Meanwhile, the feature maps on the point of the grid are adopted to generate the bounding box predictions. The point feature is convenient to use but may lack the explicit border informa…