13 accepted papers
The integration of audio modality into Large Audio Language Models (LALMs) significantly expands their attack surface. Existing jailbreak paradigms predominantly treat audio as a carrier for malicious payloads, relying on semantic optimization, acoustic parameter control, or additive perturbation to…
Machine learning models constitute valuable intellectual property, yet remain vulnerable to model extraction attacks (MEA), where adversaries replicate their functionality through black-box queries. Model watermarking counters MEAs by embedding forensic markers for ownership verification. Current bl
Overestimation in evaluating large language models (LLMs) has become an increasing concern. Due to the contamination of public benchmarks or imbalanced model training, LLMs may achieve unreal evaluation results on public benchmarks, either intentionally or unintentionally, which leads to unfair comp
AI-assisted programming is rapidly reshaping software development, with large language models (LLMs) enabling new paradigms such as vibe coding and agentic coding. While prior works have focused on prompt design and code generation quality, the broader impact of LLM-driven development on the iterati…
The advancement of 3D understanding and representation is a crucial step for the next phase of autonomous driving, robotics, augmented and virtual reality, 3D gaming and 3D e-commerce products. However, existing 3D semantic representation research has primarily focused on point clouds to perceive 3D…
Low rank adaptation (LoRA) has emerged as a prominent technique for fine-tuning large language models (LLMs) thanks to its superb efficiency gains over previous methods. While extensive studies have examined the performance and structural properties of LoRA, its behavior upon training-time attacks r…
Recent years have witnessed rapid advancements in the safety alignments of large language models (LLMs). Methods such as supervised instruction fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) have thus emerged as vital components in constructing LLMs. While these methods achi…
Machine unlearning enables the removal of specific data from ML models to uphold the *right to be forgotten*. While approximate unlearning algorithms offer efficient alternatives to full retraining, this work reveals that they fail to adequately protect the privacy of unlearned data. In particular,…
Machine learning models are often vulnerable to inference attacks that expose sensitive information from their training data. Shadow model technique is commonly employed in such attacks, like membership inference. However, the need for a large number of shadow models leads to high computational cost…
Synthetic data refers to artificial samples generated by models. While it has been validated to significantly enhance the performance of large language models (LLMs) during training and has been widely adopted in LLM development, potential security risks it may introduce remain uninvestigated. This…
Model extraction attacks (MEAs) on large language models (LLMs) have received increasing attention in recent research. However, existing attack methods typically adapt the extraction strategies originally developed for deep neural networks (DNNs). They neglect the underlying inconsistency between th…
The drastic increase in language models' parameters has led to a new trend of deploying models in cloud servers, raising growing concerns about private inference for Transformer-based models. Existing two-party privacy-preserving techniques, however, only take into account natural language understan…
Multi-action dialog policy (MADP), which generates multiple atomic dialog actions per turn, has been widely applied in task-oriented dialog systems to provide expressive and efficient system responses. Existing MADP models usually imitate action combinations from the labeled multi-action dialog samp…