相关论文: Retrofitting Fine Grain Isolation in the Firefox R…
Federated learning (FL) has emerged as a powerful approach to safeguard data privacy by training models across distributed edge devices without centralizing local data. Despite advancements in homogeneous data scenarios, maintaining…
Reconfigurable intelligent surfaces (RIS) is a revolutionary technology to cost-effectively improve the performance of wireless networks. We first review the existing framework of channel estimation and passive beamforming (CE & PBF) in…
Federated Learning (FL) plays a critical role in distributed systems. In these systems, data privacy and confidentiality hold paramount importance, particularly within edge-based data processing systems such as IoT devices deployed in smart…
While Large Language Models (LLMs) demonstrate remarkable capabilities, they remain susceptible to sophisticated, multi-step jailbreak attacks that circumvent conventional surface-level safety alignment by exploiting the internal generation…
This report investigates the relationship between software refactoring and behavior preservation. Existing behavior preservation analyses often lack comprehensive insights into refactoring rejections and do not provide actionable solutions.…
Toxic interactions during code reviews can undermine teamwork and hinder productivity in software engineering (SE) teams. While prior studies explore toxicity detection and empirical investigation, they lack real-time detoxification tools…
The application of Artificial Intelligence has become a powerful approach to detecting software vulnerabilities. However, effective vulnerability detection relies on accurately capturing the semantic structure of code and its contextual…
A well known drawback of IP-multicast is that it requires per-group state to be stored in the routers. Bloom-filter based source-routed multicast remedies this problem by moving the state from the routers to the packets. However, a fixed…
Due to the computational complexity of self-attention (SA), prevalent techniques for image deblurring often resort to either adopting localized SA or employing coarse-grained global SA methods, both of which exhibit drawbacks such as…
We introduce a new mechanism to securely extend systems data collection software with potentially untrusted third-party code. Unlike existing tools which run extension modules or plugins directly inside the monitored endpoint (the guest),…
Single Image Reflection Separation (SIRS) disentangles mixed images into transmission and reflection layers. Existing methods suffer from transmission-reflection confusion under nonlinear mixing, particularly in deep decoder layers, due to…
Verifying the serializability of transaction histories is essential for users to know if the DBMS ensures the claimed serializable isolation level without potential bugs. Black-box serializability verification is a promising approach.…
The autoregressive decoding for text generation in large language models (LLMs), while widely used, is inherently suboptimal due to the lack of a built-in mechanism to perform refinement and/or correction of the generated content. In this…
Reinforcement learning (RL) has achieved strong results, but deploying visual policies on resource-constrained edge devices remains challenging due to computational cost and communication latency. Many deployments therefore offload policy…
Greybox fuzzing is one of the most popular methods for detecting software vulnerabilities, which conducts a biased random search within the program input space. To enhance its effectiveness in achieving deep coverage of program behaviors,…
Large Language Models (LLMs) with safe-alignment training are powerful instruments with robust language comprehension capabilities. These models typically undergo meticulous alignment procedures involving human feedback to ensure the…
A common approach to protect confidential information is to use a stream cipher which combines plain text bits with a pseudo-random bit sequence. Among the existing stream ciphers, Non-Linear Feedback Shift Register (NLFSR)-based ones…
Recent works have brought attention to the vulnerability of Federated Learning (FL) systems to gradient leakage attacks. Such attacks exploit clients' uploaded gradients to reconstruct their sensitive data, thereby compromising the privacy…
Current LLM-based services typically require users to submit raw text regardless of its sensitivity. While intuitive, such practice introduces substantial privacy risks, as unauthorized access may expose personal, medical, or legal…
According to experts, one third of all IT vulnerabilities today are due to inadequate software verification. Internal program processes are not sufficiently secured against manipulation by attackers, especially if access has been gained.…