相关论文: Cordyceps: Covert Control Attacks on LLMs via Data…

We introduce a new class of attacks on machine learning models. We show that an adversary who can poison a training dataset can cause models trained on this dataset to leak significant private details of training points belonging to other…

The increasing use of large language models (LLMs) trained by third parties raises significant security concerns. In particular, malicious actors can introduce backdoors through poisoning attacks to generate undesirable outputs. While such…

In the software engineering community, deep learning (DL) has recently been applied to many source code processing tasks. Due to the poor interpretability of DL models, their security vulnerabilities require scrutiny. Recently, researchers…

Targeted data poisoning attacks manipulate model predictions on specific test samples by injecting malicious data into training. Yet existing evaluations report average attack success rates over randomly selected targets, obscuring true…

Data poisoning causes misclassification of test time target examples by injecting maliciously crafted samples in the training data. Existing defenses are often effective only against a specific type of targeted attack, significantly degrade…

It has been proved that deep neural networks are facing a new threat called backdoor attacks, where the adversary can inject backdoors into the neural network model through poisoning the training dataset. When the input containing some…

We introduce camouflaged data poisoning attacks, a new attack vector that arises in the context of machine unlearning and other settings when model retraining may be induced. An adversary first adds a few carefully crafted points to the…

Data-poisoning based backdoor attacks aim to insert backdoor into models by manipulating training datasets without controlling the training process of the target model. Existing attack methods mainly focus on designing triggers or fusion…

Large Language Models (LLMs) are widely deployed in applications that accept user-submitted content, such as uploaded documents or pasted text, for tasks like summarization and question answering. In this paper, we identify a new class of…

Data poisoning is one of the most relevant security threats against machine learning and data-driven technologies. Since many applications rely on untrusted training data, an attacker can easily craft malicious samples and inject them into…

Machine learning models have been widely adopted in several fields. However, most recent studies have shown several vulnerabilities from attacks with a potential to jeopardize the integrity of the model, presenting a new window of research…

Large Language Models (LLMs) excel in processing and generating human language, powered by their ability to interpret and follow instructions. However, their capabilities can be exploited through prompt injection attacks. These attacks…

Without direct access to the client's data, federated learning (FL) is well-known for its unique strength in data privacy protection among existing distributed machine learning techniques. However, its distributive and iterative nature…

Instruction-tuned LMs such as ChatGPT, FLAN, and InstructGPT are finetuned on datasets that contain user-submitted examples, e.g., FLAN aggregates numerous open-source datasets and OpenAI leverages examples submitted in the browser…

Supervised fine-tuning (SFT) is essential for the development of medical large language models (LLMs), yet prior poisoning studies have mainly focused on the detectable backdoor attacks. We propose a novel poisoning attack targeting the…

Backdoor data poisoning attacks have recently been demonstrated in computer vision research as a potential safety risk for machine learning (ML) systems. Traditional data poisoning attacks manipulate training data to induce unreliability of…

Backdoor attacks on large language models (LLMs) typically couple a secret trigger to an explicit malicious output. We show that this explicit association is unnecessary for common LLMs. We introduce a compliance-only backdoor: supervised…

LLM-integrated applications and agents are vulnerable to prompt injection attacks, where adversaries embed malicious instructions within seemingly benign input data to manipulate the LLM's intended behavior. Recent defenses based on…

Machine learning systems trained on user-provided data are susceptible to data poisoning attacks, whereby malicious users inject false training data with the aim of corrupting the learned model. While recent work has proposed a number of…

Vision-Language Models (VLMs) have achieved impressive progress in multimodal text generation, yet their rapid adoption raises increasing concerns about security vulnerabilities. Existing backdoor attacks against VLMs primarily rely on…