相关论文: Making Code Re-randomization Practical with MARDU

As machine learning (ML) systems are being increasingly employed in the real world to handle sensitive tasks and make decisions in various fields, the security and privacy of those models have also become increasingly critical. In…

Millions of new pieces of malicious software (i.e., malware) are introduced each year. This poses significant challenges for antivirus vendors, who use machine learning to detect and analyze malware, and must keep up with changes in the…

We develop a queueing-theoretic framework to model the temporal evolution of cyber-attack surfaces, where the number of active vulnerabilities is represented as the backlog of a queue. Vulnerabilities arrive as they are discovered or…

In this paper, we propose a novel mechanism to normalize metamorphic and obfuscated malware down at the opcode level and hence create an advanced metamorphic malware de-obfuscation and defense system. We name this system DRLDO, for Deep…

The safe application of reinforcement learning (RL) requires generalization from limited training data to unseen scenarios. Yet, fulfilling tasks under changing circumstances is a key challenge in RL. Current state-of-the-art approaches for…

Recent studies imply that deep neural networks are vulnerable to adversarial examples -- inputs with a slight but intentional perturbation are incorrectly classified by the network. Such vulnerability makes it risky for some…

As ML models are increasingly deployed in critical applications, robustness against adversarial perturbations is crucial. While numerous defenses have been proposed to counter such attacks, they typically assume that all adversarial…

Large language models (LLMs) achieve impressive performance across diverse tasks yet remain vulnerable to jailbreak attacks that bypass safety mechanisms. We present RAID (Refusal-Aware and Integrated Decoding), a framework that…

Convolutional neural networks have demonstrated high accuracy on various tasks in recent years. However, they are extremely vulnerable to adversarial examples. For example, imperceptible perturbations added to clean images can cause…

Memory bandwidth is critical in today's high performance computing systems. The bandwidth is particularly paramount for GPU workloads such as 3D Gaming, Imaging and Perceptual Computing, GPGPU due to their data-intensive nature. As the…

Retrieval-augmented generation (RAG) systems are increasingly deployed in sensitive domains such as healthcare and law, where they rely on private, domain-specific knowledge. This capability introduces significant security risks, including…

Visual language models (VLMs) have made significant progress in image captioning tasks, yet recent studies have found they are vulnerable to backdoor attacks. Attackers can inject undetectable perturbations into the data during inference,…

Machine learning (ML) has demonstrated significant advancements in Android malware detection (AMD); however, the resilience of ML against realistic evasion attacks remains a major obstacle for AMD. One of the primary factors contributing to…

Persistent memory attacks against LLM agents achieve high attack success rates against open-source models. In these attacks, malicious instructions injected via RAG-retrieved documents are stored in persistent memory and executed in later…

Resistive random-access memory (RRAM) is gaining popularity due to its ability to offer computing within the memory and its non-volatile nature. The unique properties of RRAM, such as binary switching, multi-state switching, and device…

Large Language Models (LLMs) are known to be vulnerable to jailbreaking attacks, wherein adversaries exploit carefully engineered prompts to induce harmful or unethical responses. Such threats have raised critical concerns about the safety…

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse applications, yet they pose significant security risks that threaten their safe deployment in critical domains. Current security alignment methodologies…

In this paper, we show that coding can be used in storage area networks (SANs) to improve various quality of service metrics under normal SAN operating conditions, without requiring additional storage space. For our analysis, we develop a…

Malware detectors based on deep learning (DL) have been shown to be susceptible to malware examples that have been deliberately manipulated in order to evade detection, a.k.a. adversarial malware examples. More specifically, it has been…

Retrieval-Augmented Generation (RAG) has become a cornerstone of knowledge-intensive applications, including enterprise chatbots, healthcare assistants, and agentic memory management. However, recent studies show that knowledge-extraction…