相关论文: DyePack: Provably Flagging Test Set Contamination …

Backdoor attacks pose a significant security vulnerability for deep neural networks (DNNs), enabling them to operate normally on clean inputs but manipulate predictions when specific trigger patterns occur. Currently, post-training backdoor…

Public benchmarks increasingly govern how large language models (LLMs) are ranked, selected, and deployed. We frame this benchmark-centered regime as Silicon Bureaucracy and AI Test-Oriented Education, and argue that it rests on a fragile…

In this position paper, we argue that the classical evaluation on Natural Language Processing (NLP) tasks using annotated benchmarks is in trouble. The worst kind of data contamination happens when a Large Language Model (LLM) is trained on…

The training process of large language models (LLMs) often involves varying degrees of test data contamination. Although current LLMs are achieving increasingly better performance on various benchmarks, their performance in practical…

Recent benchmark efforts have advanced the evaluation of large language models (LLMs) in cybersecurity, including tasks such as penetration testing and vulnerability identification. However, a critical cybersecurity task, namely intrusion…

In recent years, large language models (LLMs) have demonstrated notable success across various tasks, but the trustworthiness of LLMs is still an open problem. One specific threat is the potential to generate toxic or harmful responses.…

Large Language Models (LLMs) are of great interest in vulnerability detection and repair. The effectiveness of these models hinges on the quality of the datasets used for both training and evaluation. Our investigation reveals that a number…

Public resources and services (e.g., datasets, training platforms, pre-trained models) have been widely adopted to ease the development of Deep Learning-based applications. However, if the third-party providers are untrusted, they can…

The rapid advancements of Large Language Models (LLMs) tightly associate with the expansion of the training data size. However, the unchecked ultra-large-scale training sets introduce a series of potential risks like data contamination,…

Data contamination hinders fair LLM evaluation by introducing test data into newer models' training sets. Existing studies solve this challenge by updating benchmarks with newly collected data. However, they fail to guarantee…

Deep learning (DL) compilers are core infrastructure in modern DL systems, offering flexibility and scalability beyond vendor-specific libraries. This work uncovers a fundamental vulnerability in their design: can an official, unmodified…

Public leaderboards increasingly suggest that large language models (LLMs) surpass human experts on benchmarks spanning academic knowledge, law, and programming. Yet most benchmarks are fully public, their questions widely mirrored across…

Large-scale language models have achieved tremendous success across various natural language processing (NLP) applications. Nevertheless, language models are vulnerable to backdoor attacks, which inject stealthy triggers into models for…

Recently, DL has been exploited in wireless communications such as modulation classification. However, due to the openness of wireless channel and unexplainability of DL, it is also vulnerable to adversarial attacks. In this correspondence,…

The prevalence of malicious packages in open-source repositories, such as PyPI, poses a critical threat to the software supply chain. While Large Language Models (LLMs) have emerged as a promising tool for automated security tasks, their…

Chat template is a common technique used in the training and inference stages of Large Language Models (LLMs). It can transform input and output data into role-based and templated expressions to enhance the performance of LLMs. However,…

The financial industry relies on deep learning models for making important decisions. This adoption brings new danger, as deep black-box models are known to be vulnerable to adversarial attacks. In computer vision, one can shape the output…

Pre-trained language models (PLMs) have demonstrated remarkable performance as few-shot learners. However, their security risks under such settings are largely unexplored. In this work, we conduct a pilot study showing that PLMs as few-shot…

As backdoor attacks become more stealthy and robust, they reveal critical weaknesses in current defense strategies: detection methods often rely on coarse-grained feature statistics, and purification methods typically require full…

Backdoor attacks pose a serious security threat for training neural networks as they surreptitiously introduce hidden functionalities into a model. Such backdoors remain silent during inference on clean inputs, evading detection due to…