Related papers: T-MLA: A targeted multiscale log-exponential attac…

Deep neural networks are known to be vulnerable to adversarial perturbations, which are small and carefully crafted inputs that lead to incorrect predictions. In this paper, we propose DeepDefense, a novel defense framework that applies…

Robustness evaluation against adversarial examples has become increasingly important to unveil the trustworthiness of the prevailing deep models in natural language processing (NLP). However, in contrast to the computer vision domain where…

The volume of machine-generated content online has grown dramatically due to the widespread use of Large Language Models (LLMs), leading to new challenges for content moderation systems. Conventional content moderation classifiers, which…

Content Warning: This paper may contain unsafe or harmful content generated by LLMs that may be offensive to readers. Large Language Models (LLMs) increasingly serve as tooling platforms through structured output APIs, but the…

The widespread adoption of learning-based methods for the LiDAR makes autonomous vehicles vulnerable to adversarial attacks through adversarial \textit{point injections (PiJ)}. It poses serious security challenges for navigation and map…

Addressing the escalating security vulnerabilities in Vision-Language-Action (VLA) models, this study investigates backdoor attacks targeting the visual pathway. We identify a core obstacle causing the failure of traditional attack…

IoT devices are increasingly the source of data for machine learning (ML) applications running on edge servers. Data transmissions from devices to servers are often over local wireless networks whose bandwidth is not just limited but, more…

Deep neural networks (DNNs) have been demonstrated to be vulnerable to adversarial examples. Specifically, adding imperceptible perturbations to clean images can fool the well trained deep neural networks. In this paper, we propose an…

Despite their performance, Artificial Neural Networks are not reliable enough for most of industrial applications. They are sensitive to noises, rotations, blurs and adversarial examples. There is a need to build defenses that protect…

Graph Neural Networks (GNNs) have emerged as powerful models for learning from graph-structured data. However, their widespread adoption has raised serious privacy concerns. While prior research has primarily focused on edge-level privacy,…

Most discussions about Large Language Model (LLM) safety have focused on single-agent settings but multi-agent LLM systems now create novel adversarial risks because their behavior depends on communication between agents and decentralized…

Deep neural networks have proven to be quite effective in a wide variety of machine learning tasks, ranging from improved speech recognition systems to advancing the development of autonomous vehicles. However, despite their superior…

Learning and compression are driven by the common aim of identifying and exploiting statistical regularities in data, which opens the door for fertile collaboration between these areas. A promising group of compression techniques for…

Multimodal Large Language Models (MLLMs), built upon LLMs, have recently gained attention for their capabilities in image recognition and understanding. However, while MLLMs are vulnerable to adversarial attacks, the transferability of…

The main premise of federated learning (FL) is that machine learning model updates are computed locally to preserve user data privacy. This approach avoids by design user data to ever leave the perimeter of their device. Once the updates…

Learned image compression (LIC) is becoming more and more popular these years with its high efficiency and outstanding compression quality. Still, the practicality against modified inputs added with specific noise could not be ignored.…

The security of Large Language Model (LLM) applications is fundamentally challenged by "form-first" attacks like prompt injection and jailbreaking, where malicious instructions are embedded within user inputs. Conventional defenses, which…

Pretrained vision-language models (VLMs) like CLIP exhibit exceptional generalization across diverse downstream tasks. While recent studies reveal their vulnerability to adversarial attacks, research to date has primarily focused on…

Reducing the key-value (KV) cache size is a crucial step toward enabling efficient inference in large language models (LLMs), especially under latency and memory constraints. While Multi-Head Attention (MHA) offers strong representational…

The outstanding performance of large foundational models across diverse tasks, from computer vision to speech and natural language processing, has significantly increased their demand. However, storing and transmitting these models poses…