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

Recently, deep Reinforcement Learning (RL) algorithms have achieved dramatically progress in the multi-agent area. However, training the increasingly complex tasks would be time-consuming and resources-exhausting. To alleviate this problem,…

Android malware attacks have posed a severe threat to mobile users, necessitating a significant demand for the automated detection system. Among the various tools employed in malware detection, graph representations (e.g., function call…

The field of textual adversarial defenses has gained considerable attention in recent years due to the increasing vulnerability of natural language processing (NLP) models to adversarial attacks, which exploit subtle perturbations in input…

Neural ranking models have achieved remarkable progress and are now widely deployed in real-world applications such as Retrieval-Augmented Generation (RAG). However, like other neural architectures, they remain vulnerable to adversarial…

Over the past decade, there has been extensive research aimed at enhancing the robustness of neural networks, yet this problem remains vastly unsolved. Here, one major impediment has been the overestimation of the robustness of new defense…

Despite excellent performance on many tasks, NLP systems are easily fooled by small adversarial perturbations of inputs. Existing procedures to defend against such perturbations are either (i) heuristic in nature and susceptible to stronger…

Retrieval-Augmented Code Generation (RACG) is increasingly adopted to enhance Large Language Models for software development, yet its security implications remain dangerously underexplored. This paper conducts the first systematic…

The explosion of the amount of data stored in cloud systems calls for more efficient paradigms for redundancy. While replication is widely used to ensure data availability, erasure correcting codes provide a much better trade-off between…

Adversarial attacks pose a challenge to the deployment of deep neural networks (DNNs), while previous defense models overlook the generalization to various attacks. Inspired by targeted therapies for cancer, we view adversarial samples as…

Software protection aims at safeguarding assets embedded in software by preventing and delaying reverse engineering and tampering attacks. This paper presents an architecture and supporting tool flow to renew parts of native applications…

As adversarial attacks continue to evolve, defense models face the risk of recurrent vulnerabilities, underscoring the importance of continuous adversarial training (CAT). Existing CAT approaches typically balance decision boundaries by…

Large language models (LLMs) have demonstrated impressive capabilities in code generation by leveraging retrieval-augmented generation (RAG) methods. However, the computational costs associated with LLM inference, particularly in terms of…

Preprocessing defenses such as pixel discretization are appealing to remove adversarial attacks due to their simplicity. However, they have been shown to be ineffective except on simple datasets like MNIST. We hypothesize that existing…

Disaggregated memory leverages recent technology advances in high-density, byte-addressable non-volatile memory and high-performance interconnects to provide a large memory pool shared across multiple compute nodes. Due to higher memory…

Machine Learning (ML) techniques can facilitate the automation of malicious software (malware for short) detection, but suffer from evasion attacks. Many studies counter such attacks in heuristic manners, lacking theoretical guarantees and…

The structural re-parameterization (SRP) technique is a novel deep learning technique that achieves interconversion between different network architectures through equivalent parameter transformations. This technique enables the mitigation…

Deep learning-based adversarial malware detectors have yielded promising results in detecting never-before-seen malware executables without relying on expensive dynamic behavior analysis and sandbox. Despite their abilities, these detectors…

Deep Neural Network (DNN) trained by the gradient descent method is known to be vulnerable to maliciously perturbed adversarial input, aka. adversarial attack. As one of the countermeasures against adversarial attack, increasing the model…

This article investigates the security issue caused by false data injection attacks in distributed estimation, wherein each sensor can construct two types of residues based on local estimates and neighbor information, respectively. The…

Machine Learning as a Service (MLaaS) enables users to leverage powerful machine learning models through cloud-based APIs, offering scalability and ease of deployment. However, these services are vulnerable to model extraction attacks,…