Related papers: Combing for Credentials: Active Pattern Extraction…

Information leakage is becoming a critical problem as various information becomes publicly available by mistake, and machine learning models train on that data to provide services. As a result, one's private information could easily be…

Deep learning has transformed AI applications but faces critical security challenges, including adversarial attacks, data poisoning, model theft, and privacy leakage. This survey examines these vulnerabilities, detailing their mechanisms…

Adversarial attacks pose a major threat to machine learning and to the systems that rely on it. In the cybersecurity domain, adversarial cyber-attack examples capable of evading detection are especially concerning. Nonetheless, an example…

Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level,…

Model explanations provide transparency into a trained machine learning model's blackbox behavior to a model builder. They indicate the influence of different input attributes to its corresponding model prediction. The dependency of…

Although Large Language Models (LLMs) have become increasingly integral to diverse applications, their capabilities raise significant privacy concerns. This survey offers a comprehensive overview of privacy risks associated with LLMs and…

Users interacting with large language models (LLMs) under their real identifiers often unknowingly risk disclosing private information. Automatically notifying users whether their queries leak privacy and which phrases leak what private…

System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications. These instructions may contain sensitive…

Large language models (LLMs) are now routinely used to autonomously execute complex tasks, from natural language processing to dynamic workflows like web searches. The usage of tool-calling and Retrieval Augmented Generation (RAG) allows…

Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. By tampering with a pretrained…

Thanks to the explosive growth of data and the development of computational resources, it is possible to build pre-trained models that can achieve outstanding performance on various tasks, such as neural language processing, computer…

Neural networks are widely known to be vulnerable to backdoor attacks, a method that poisons a portion of the training data to make the target model perform well on normal data sets, while outputting attacker-specified or random categories…

Reconstruction attacks allow an adversary to regenerate data samples of the training set using access to only a trained model. It has been recently shown that simple heuristics can reconstruct data samples from language models, making this…

With the growing burden of training deep learning models with large data sets, transfer-learning has been widely adopted in many emerging deep learning algorithms. Transformer models such as BERT are the main player in natural language…

In collaborative learning, clients keep their data private and communicate only the computed gradients of the deep neural network being trained on their local data. Several recent attacks show that one can still extract private information…

This paper introduces a new attack on recent messaging systems that protect communication metadata. The main observation is that if an adversary manages to compromise a user's friend, it can use this compromised friend to learn information…

Language Models (LMs) have been shown to leak information about training data through sentence-level membership inference and reconstruction attacks. Understanding the risk of LMs leaking Personally Identifiable Information (PII) has…

Recent work has shown it is possible to construct adversarial examples that cause an aligned language model to emit harmful strings or perform harmful behavior. Existing attacks work either in the white-box setting (with full access to the…

Collaborative machine learning and related techniques such as federated learning allow multiple participants, each with his own training dataset, to build a joint model by training locally and periodically exchanging model updates. We…

Training AI models in cybersecurity with help of vast datasets offers significant opportunities to mimic real-world behaviors effectively. However, challenges like data drift and scarcity of labelled data lead to frequent updates of models…