相关论文: Exploiting Leaderboards for Large-Scale Distributi…

Recently, it has been shown that deep learning models are vulnerable to Trojan attacks, where an attacker can install a backdoor during training time to make the resultant model misidentify samples contaminated with a small trigger patch.…

The recent success of machine learning (ML) has been fueled by the increasing availability of computing power and large amounts of data in many different applications. However, the trustworthiness of the resulting models can be compromised…

Neural networks can conceal malicious Trojan backdoors that allow a trigger to covertly change the model behavior. Detecting signs of these backdoors, particularly without access to any triggered data, is the subject of ongoing research and…

Deep learning has come a long way and has enjoyed an unprecedented success. Despite high accuracy, however, deep models are brittle and are easily fooled by imperceptible adversarial perturbations. In contrast to common inference-time…

Data poisoning and leakage risks impede the massive deployment of federated learning in the real world. This chapter reveals the truths and pitfalls of understanding two dominating threats: {\em training data privacy intrusion} and {\em…

We present a Trojan (backdoor or trapdoor) attack that targets deep learning applications in wireless communications. A deep learning classifier is considered to classify wireless signals using raw (I/Q) samples as features and modulation…

Backdoor (trojan) attacks embed hidden, controllable behaviors into machine-learning models so that models behave normally on benign inputs but produce attacker-chosen outputs when a trigger is present. This survey reviews the rapidly…

A backdoor or Trojan attack is an important type of data poisoning attack against deep neural network (DNN) classifiers, wherein the training dataset is poisoned with a small number of samples that each possess the backdoor pattern (usually…

Model merging has emerged as a powerful technique for combining specialized capabilities from multiple fine-tuned LLMs without additional training costs. However, the security implications of this widely-adopted practice remain critically…

Wild images on the web are vulnerable to backdoor (also called trojan) poisoning, causing machine learning models learned on these images to be injected with backdoors. Most previous attacks assumed that the wild images are labeled. In…

Backdoor attacks manipulate model predictions by inserting innocuous triggers into training and test data. We focus on more realistic and more challenging clean-label attacks where the adversarial training examples are correctly labeled.…

In this work, we show how to jointly exploit adversarial perturbation and model poisoning vulnerabilities to practically launch a new stealthy attack, dubbed AdvTrojan. AdvTrojan is stealthy because it can be activated only when: 1) a…

With tools like GitHub Copilot, automatic code suggestion is no longer a dream in software engineering. These tools, based on large language models, are typically trained on massive corpora of code mined from unvetted public sources. As a…

Recent advances in federated learning have demonstrated its promising capability to learn on decentralized datasets. However, a considerable amount of work has raised concerns due to the potential risks of adversaries participating in the…

Training pipelines for machine learning (ML) based malware classification often rely on crowdsourced threat feeds, exposing a natural attack injection point. In this paper, we study the susceptibility of feature-based ML malware classifiers…

In adversarial machine learning, new defenses against attacks on deep learning systems are routinely broken soon after their release by more powerful attacks. In this context, forensic tools can offer a valuable complement to existing…

As in-the-wild data are increasingly involved in the training stage, machine learning applications become more susceptible to data poisoning attacks. Such attacks typically lead to test-time accuracy degradation or controlled misprediction.…

The training phase of machine learning models is a delicate step, especially in cybersecurity contexts. Recent research has surfaced a series of insidious training-time attacks that inject backdoors in models designed for security…

Robotic manipulation policies are increasingly empowered by \textit{large language models} (LLMs) and \textit{vision-language models} (VLMs), leveraging their understanding and perception capabilities. Recently, inference-time attacks…

Deep learning models have achieved high performance on many tasks, and thus have been applied to many security-critical scenarios. For example, deep learning-based face recognition systems have been used to authenticate users to access many…