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

In machine learning Trojan attacks, an adversary trains a corrupted model that obtains good performance on normal data but behaves maliciously on data samples with certain trigger patterns. Several approaches have been proposed to detect…

Large language models (LLMs) have revolutionized software development practices, yet concerns about their safety have arisen, particularly regarding hidden backdoors, aka trojans. Backdoor attacks involve the insertion of triggers into…

The growing dependence on machine learning in real-world applications emphasizes the importance of understanding and ensuring its safety. Backdoor attacks pose a significant security risk due to their stealthy nature and potentially serious…

Deep neural networks are known to have security issues. One particular threat is the Trojan attack. It occurs when the attackers stealthily manipulate the model's behavior through Trojaned training samples, which can later be exploited.…

Large Language Models (LLMs) are seeing significant adoption in every type of organization due to their exceptional generative capabilities. However, LLMs are found to be vulnerable to various adversarial attacks, particularly prompt…

Modern machine learning (ML) ecosystems offer a surging number of ML frameworks and code repositories that can greatly facilitate the development of ML models. Today, even ordinary data holders who are not ML experts can apply off-the-shelf…

Research in adversarial machine learning has shown how the performance of machine learning models can be seriously compromised by injecting even a small fraction of poisoning points into the training data. While the effects on model…

Large Language Models (LLMs) are progressively being utilized as machine learning services and interface tools for various applications. However, the security implications of LLMs, particularly in relation to adversarial and Trojan attacks,…

Deep neural networks are vulnerable to adversarial attacks, where a small perturbation to an input alters the model prediction. In many cases, malicious inputs intentionally crafted for one model can fool another model. In this paper, we…

Instruction tuning is an effective technique to align large language models (LLMs) with human intents. In this work, we investigate how an adversary can exploit instruction tuning by injecting specific instruction-following examples into…

Data poisoning is an attack on machine learning models wherein the attacker adds examples to the training set to manipulate the behavior of the model at test time. This paper explores poisoning attacks on neural nets. The proposed attacks…

Textual backdoor attacks are a kind of practical threat to NLP systems. By injecting a backdoor in the training phase, the adversary could control model predictions via predefined triggers. As various attack and defense models have been…

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…

With the widespread use of deep neural networks (DNNs) in high-stake applications, the security problem of the DNN models has received extensive attention. In this paper, we investigate a specific security problem called trojan attack,…

Backdoors and poisoning attacks are a major threat to the security of machine-learning and vision systems. Often, however, these attacks leave visible artifacts in the images that can be visually detected and weaken the efficacy of the…

Trojan backdoors can be injected into large language models at various stages, including pretraining, fine-tuning, and in-context learning, posing a significant threat to the model's alignment. Due to the nature of causal language modeling,…

Growing applications of large language models (LLMs) trained by a third party raise serious concerns on the security vulnerability of LLMs.It has been demonstrated that malicious actors can covertly exploit these vulnerabilities in LLMs…

We investigate security concerns of the emergent instruction tuning paradigm, that models are trained on crowdsourced datasets with task instructions to achieve superior performance. Our studies demonstrate that an attacker can inject…

Semi-supervised machine learning models learn from a (small) set of labeled training examples, and a (large) set of unlabeled training examples. State-of-the-art models can reach within a few percentage points of fully-supervised training,…

Large Language Models (LLMs) have greatly advanced Natural Language Processing (NLP), particularly through instruction tuning, which enables broad task generalization without additional fine-tuning. However, their reliance on large-scale…