相关论文: Non-control-Data Attacks and Defenses: A review

Backdoor attacks represent a subtle yet effective class of cyberattacks targeting AI models, primarily due to their stealthy nature. The model behaves normally on clean data but exhibits malicious behavior only when the attacker embeds a…

With the advancement of technology, large language models (LLMs) have achieved remarkable performance across various natural language processing (NLP) tasks, powering LLM-integrated applications like Microsoft Copilot. However, as LLMs…

Existing data-driven control methods generally do not address False Data Injection (FDI) and Denial-of-Service (DoS) attacks simultaneously. This letter introduces a distributed data-driven attack-resilient consensus problem under both FDI…

In a macro-economic system, all major sectors: agriculture, extraction of natural resources, manufacturing, construction, transport, communication and health services, are dependent on a reliable supply of electricity. Targeted attacks on…

The unprecedented availability of training data fueled the rapid development of powerful neural networks in recent years. However, the need for such large amounts of data leads to potential threats such as poisoning attacks: adversarial…

Data poisoning is a threat model in which a malicious actor tampers with training data to manipulate outcomes at inference time. A variety of defenses against this threat model have been proposed, but each suffers from at least one of the…

Backdoor attacks (BA) are an emerging threat to deep neural network classifiers. A classifier being attacked will predict to the attacker's target class when a test sample from a source class is embedded with the backdoor pattern (BP).…

Local Differential Privacy (LDP) protocols enable an untrusted data collector to perform privacy-preserving data analytics. In particular, each user locally perturbs its data to preserve privacy before sending it to the data collector, who…

The Denial of Wallet (DoW) attack poses a unique and growing threat to serverless architectures that rely on Function-as-a-Service (FaaS) models, exploiting the cost structure of pay-as-you-go billing to financially burden application…

Security protocols are often found to be flawed after their deployment. We present an approach that aims at the neutralization or mitigation of the attacks to flawed protocols: it avoids the complete dismissal of the interested protocol and…

Machine learning techniques have been widely applied to various applications. However, they are potentially vulnerable to data poisoning attacks, where sophisticated attackers can disrupt the learning procedure by injecting a fraction of…

Clean-label (CL) attack is a form of data poisoning attack where an adversary modifies only the textual input of the training data, without requiring access to the labeling function. CL attacks are relatively unexplored in NLP, as compared…

Data Loss/Leakage Prevention (DLP) continues to be the main issue for many large organizations. There are multiple numbers of emerging security attach scenarios and a limitless number of overcoming solutions. Today's enterprises' major…

Public intelligent services enabled by machine learning algorithms are vulnerable to model extraction attacks that can steal confidential information of the learning models through public queries. Though there are some protection options…

Machine learning systems are deployed in critical settings, but they might fail in unexpected ways, impacting the accuracy of their predictions. Poisoning attacks against machine learning induce adversarial modification of data used by a…

Trojan attacks on deep neural networks are both dangerous and surreptitious. Over the past few years, Trojan attacks have advanced from using only a single input-agnostic trigger and targeting only one class to using multiple,…

Selective data protection is a promising technique to defend against the data leakage attack. In this paper, we revisit technical challenges that were neglected when applying this protection to real applications. These challenges include…

Data-poisoning backdoor attacks are serious security threats to machine learning models, where an adversary can manipulate the training dataset to inject backdoors into models. In this paper, we focus on in-training backdoor defense, aiming…

Website fingerprinting (WF) attacks, which covertly monitor user communications to identify the web pages they visit, pose a serious threat to user privacy. Existing WF defenses attempt to reduce attack accuracy by disrupting traffic…

Protecting programs against control-flow hijacking attacks recently has become an arms race between defenders and attackers. While certain defenses, e.g., \textit{Control Flow Integrity} (CFI), restrict the targets of indirect control-flow…