Related papers: AST-PAC: AST-guided Membership Inference for Code

In this paper, we present an optimal metric function on average, which leads to a significantly low decoding computation while maintaining the superiority of the polarization-adjusted convolutional (PAC) codes' error-correction performance.…

Membership inference attacks (MIAs) aim to determine whether a specific example was used to train a given language model. While prior work has explored prompt-based attacks such as ReCALL, these methods rely heavily on the assumption that…

Retrieval-Augmented Generation (RAG) enhances large language models by integrating external knowledge, but reliance on proprietary or sensitive corpora poses various data risks, including privacy leakage and unauthorized data usage.…

While Retrieval-Augmented Generation (RAG) effectively reduces hallucinations by integrating external knowledge bases, it introduces vulnerabilities to membership inference attacks (MIAs), particularly in systems handling sensitive data.…

Programming language understanding and representation (a.k.a code representation learning) has always been a hot and challenging task in software engineering. It aims to apply deep learning techniques to produce numerical representations of…

Machine learning (ML) models have been widely applied to various applications, including image classification, text generation, audio recognition, and graph data analysis. However, recent studies have shown that ML models are vulnerable to…

Membership Inference Attacks (MIAs) aim to predict whether a data sample belongs to the model's training set or not. Although prior research has extensively explored MIAs in Large Language Models (LLMs), they typically require accessing to…

Large language models remain vulnerable to jailbreak attacks, yet we still lack a systematic understanding of how jailbreak success scales with attacker effort across methods, model families, and harm types. We initiate a scaling-law…

Most membership inference attacks (MIAs) against Large Language Models (LLMs) rely on global signals, like average loss, to identify training data. This approach, however, dilutes the subtle, localized signals of memorization, reducing…

We consider unsupervised domain adaptation (UDA) for semantic segmentation in which the model is trained on a labeled source dataset and adapted to an unlabeled target dataset. Unfortunately, current self-training methods are susceptible to…

Recent research indicates that large language models (LLMs) are susceptible to jailbreaking attacks that can generate harmful content. This paper introduces a novel token-level attack method, Adaptive Dense-to-Sparse Constrained…

Membership Inference Attacks (MIAs) serve as a fundamental auditing tool for evaluating training data leakage in machine learning models. However, existing methodologies predominantly rely on static, handcrafted heuristics that lack…

In this paper, we introduce a novel rate-profile design based on search-constrained optimization techniques to assess the performance of polarization-adjusted convolutional (PAC) codes under Fano (sequential) decoding. The results…

Membership inference attacks (MIAs) aim to determine whether a sample was part of a model's training set, posing serious privacy risks for modern machine-learning systems. Existing MIAs primarily rely on static indicators, such as loss or…

Large language models are susceptible to jailbreak attacks, which can result in the generation of harmful content. While prior defenses mitigate these risks by perturbing or inspecting inputs, they ignore competing objectives, the…

Despite efforts to align large language models (LLMs) with societal and moral values, these models remain susceptible to jailbreak attacks -- methods designed to elicit harmful responses. Jailbreaking black-box LLMs is considered…

Membership inference attacks (MIA) can reveal whether a particular data point was part of the training dataset, potentially exposing sensitive information about individuals. This article provides theoretical guarantees by exploring the…

Large Multimodal Language Models (MLLMs) are emerging as one of the foundational tools in an expanding range of applications. Consequently, understanding training-data leakage in these systems is increasingly critical. Log-probability-based…

Large language models (LLMs) have shown great potential in code-related tasks, yet open-source models lag behind their closed-source counterparts. To bridge this performance gap, existing methods generate vast amounts of synthetic data for…

Ensuring safety alignment is a critical requirement for large language models (LLMs), particularly given increasing deployment in real-world applications. Despite considerable advancements, LLMs remain susceptible to jailbreak attacks,…