相关论文: AST-PAC: AST-guided Membership Inference for Code

Large Language Models (LLMs) have the promise to revolutionize computing broadly, but their complexity and extensive training data also expose significant privacy vulnerabilities. One of the simplest privacy risks associated with LLMs is…

Abstract syntax tree (AST) mapping algorithms are widely used to analyze changes in source code. Despite the foundational role of AST mapping algorithms, little effort has been made to evaluate the accuracy of AST mapping algorithms, i.e.,…

Polar coding gives rise to the first explicit family of codes that provably achieve capacity with efficient encoding and decoding for a wide range of channels. However, its performance at short block lengths is far from optimal. Arikan has…

Large language model-based multi-agent systems (LLM-MAS) effectively accomplish complex and dynamic tasks through inter-agent communication, but this reliance introduces substantial safety vulnerabilities. Existing attack methods targeting…

Membership Inference Attacks (MIAs) determine whether a specific data point was included in the training set of a target model. In this paper, we introduce the Semantic Membership Inference Attack (SMIA), a novel approach that enhances MIA…

The remarkable success of Large Language Models (LLMs) relies heavily on their substantial scale, which poses significant challenges during model deployment in terms of latency and memory consumption. Recently, numerous studies have…

Parameter-Efficient Fine-Tuning (PEFT) has become a key strategy for adapting large language models, with recent advances in sparse tuning reducing overhead by selectively updating key parameters or subsets of data. Existing approaches…

Membership Inference Attacks (MIAs) infer whether a data point is in the training data of a machine learning model. It is a threat while being in the training data is private information of a data point. MIA correctly infers some data…

Membership Inference (MI) poses a substantial privacy threat to the training data of Automatic Speech Recognition (ASR) systems, while also offering an opportunity to audit these models with regard to user data. This paper explores the…

Large language models (LLMs) show strong performance across many applications, but their ability to memorize and potentially reveal training data raises serious privacy concerns. We introduce the PopQuiz Attack, a black-box membership…

Recently, a novel variation of polar codes known as polarization-adjusted convolutional (PAC) codes has been introduced by Ar{\i}kan. These codes significantly outperform conventional polar and convolutional codes, particularly for short…

Safety classifiers are essential safeguards within generative AI systems, filtering harmful content or identifying at-risk users when interacting with large language models. Despite their necessity, these models are trained on sensitive…

Membership inference attacks (MIAs), which enable adversaries to determine whether specific data points were part of a model's training dataset, have emerged as an important framework to understand, assess, and quantify the potential…

Large language models (LLMs) have become essential tools for digital task assistance. Their training relies heavily on the collection of vast amounts of data, which may include copyright-protected or sensitive information. Recent studies on…

Attribute-efficient PAC learning of sparse halfspaces has been a fundamental problem in machine learning theory. In recent years, machine learning algorithms are faced with prevalent data corruptions or even malicious attacks. It is of…

The use of large language models (LLMs) in peer review systems has attracted growing attention, making it essential to examine their potential vulnerabilities. Prior attacks rely on prompt injection, which alters manuscript content and…

Over-parameterized models are typically vulnerable to membership inference attacks, which aim to determine whether a specific sample is included in the training of a given model. Previous Weight regularizations (e.g., L1 regularization)…

Large language models (LLMs) have achieved remarkable success across diverse applications but remain vulnerable to jailbreak attacks, where attackers craft prompts that bypass safety alignment and elicit unsafe responses. Among existing…

Detecting parallelizable code regions is a challenging task, even for experienced developers. Numerous recent studies have explored the use of machine learning for code analysis and program synthesis, including parallelization, in light of…

Large language models (LLMs) are effective for automated program repair, but plausible patches that pass the full test suite often rewrite more code than necessary, increasing review and maintenance costs. This over-editing is common…