Related papers: LightDE: A Lightweight Method for Eliminating Dang…

In this paper we study a cybersecurity problem of protecting system's secrets with multiple protections and a required security level, while minimizing the associated cost due to implementation/maintenance of these protections as well as…

Dead code introduces several challenges in software development, such as increased binary size and maintenance difficulties. It can also obscure logical errors and be exploited for obfuscation in malware. For LLM-based code-related tasks,…

The space of task-agnostic feature upsampling has emerged as a promising area of research to efficiently create denser features from pre-trained visual backbones. These methods act as a shortcut to achieve dense features for a fraction of…

Anomaly detection is widely used in a broad range of domains from cybersecurity to manufacturing, finance, and so on. Deep learning based anomaly detection has recently drawn much attention because of its superior capability of recognizing…

In recent years, advanced U-like networks have demonstrated remarkable performance in medical image segmentation tasks. However, their drawbacks, including excessive parameters, high computational complexity, and slow inference speed, pose…

System prompts are widely used to guide the outputs of large language models (LLMs). These prompts often contain business logic and sensitive information, making their protection essential. However, adversarial and even regular user queries…

Light-based adversarial attacks use spatial augmented reality (SAR) techniques to fool image classifiers by altering the physical light condition with a controllable light source, e.g., a projector. Compared with physical attacks that place…

Wireless sensor network comprises of small sensor nodes with limited resources. Clustered networks have been proposed in many researches to reduce the power consumption in sensor networks. LEACH is one of the most interested techniques that…

Detecting software vulnerabilities is critical to ensuring the security and reliability of modern computer systems. Deep neural networks have shown promising results on vulnerability detection, but they lack the capability to capture global…

Software vulnerabilities pose significant risks to computer systems, impacting our daily lives, productivity, and even our health. Identifying and addressing security vulnerabilities in a timely manner is crucial to prevent hacking and data…

Jailbreaking attacks on the vision modality typically rely on imperceptible adversarial perturbations, whereas attacks on the textual modality are generally assumed to require visible modifications (e.g., non-semantic suffixes). In this…

Verifiers are auxiliary models that assess the correctness of outputs generated by base large language models (LLMs). They play a crucial role in many strategies for solving reasoning-intensive problems with LLMs. Typically, verifiers are…

Rapid advances in the capabilities of large language models (LLMs) have raised widespread concerns regarding their potential for malicious use. Open-weight LLMs present unique challenges, as existing safeguards lack robustness to tampering…

The success of Google's Pregel framework in distributed graph processing has inspired a surging interest in developing Pregel-like platforms featuring a user-friendly "think like a vertex" programming model. Existing Pregel-like systems…

With the increase in software vulnerabilities that cause significant economic and social losses, automatic vulnerability detection has become essential in software development and maintenance. Recently, large language models (LLMs) like GPT…

Pointer analysis is indispensable for effectively verifying heap-manipulating programs. Even though it has been studied extensively, there are no publicly available pointer analyses that are moderately precise while scalable to large…

System prompts that include detailed instructions to describe the task performed by the underlying LLM can easily transform foundation models into tools and services with minimal overhead. They are often considered intellectual property,…

Hidden LLM prompts have appeared in online documents with increasing frequency. Their goal is to trigger indirect prompt injection attacks while remaining undetected from human oversight, to manipulate LLM-powered automated document…

A blind spot is any input to a program that can be arbitrarily mutated without affecting the program's output. Blind spots can be used for steganography or to embed malware payloads. If blind spots overlap file format keywords, they…

Adversarial fine-tuning methods enhance adversarial robustness via fine-tuning the pre-trained model in an adversarial training manner. However, we identify that some specific latent features of adversarial samples are confused by…