Related papers: Backdoors in Code Summarizers: How Bad Is It?
Recently, advanced NLP models have seen a surge in the usage of various applications. This raises the security threats of the released models. In addition to the clean models' unintentional weaknesses, {\em i.e.,} adversarial attacks, the…
Code models, such as CodeBERT and CodeT5, offer general-purpose representations of code and play a vital role in supporting downstream automated software engineering tasks. Most recently, code models were revealed to be vulnerable to…
Fine-tuned Large Language Models (LLMs) are vulnerable to backdoor attacks through data poisoning, yet the internal mechanisms governing these attacks remain a black box. Previous research on interpretability for LLM safety tends to focus…
As collaborative learning allows joint training of a model using multiple sources of data, the security problem has been a central concern. Malicious users can upload poisoned data to prevent the model's convergence or inject hidden…
Driven by the rapid development of Large Language Models (LLMs), LLM-based agents have been developed to handle various real-world applications, including finance, healthcare, and shopping, etc. It is crucial to ensure the reliability and…
Large language models (LLMs) have transformed the development of embodied intelligence. By providing a few contextual demonstrations, developers can utilize the extensive internal knowledge of LLMs to effortlessly translate complex tasks…
While previous research backdoored neural networks by changing their parameters, recent work uncovered a more insidious threat: backdoors embedded within the definition of the network's architecture. This involves injecting common…
Large language models (LLMs) have gained widespread adoption across diverse applications due to their impressive generative capabilities. Their plug-and-play nature enables both developers and end users to interact with these models through…
Federated learning security research has predominantly focused on backdoor threats from a minority of malicious clients that intentionally corrupt model updates. This paper challenges this paradigm by investigating a more pervasive and…
Recent works have demonstrated that deep learning models are vulnerable to backdoor poisoning attacks, where these attacks instill spurious correlations to external trigger patterns or objects (e.g., stickers, sunglasses, etc.). We find…
Recent studies have verified that semi-supervised learning (SSL) is vulnerable to data poisoning backdoor attacks. Even a tiny fraction of contaminated training data is sufficient for adversaries to manipulate up to 90\% of the test outputs…
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…
Backdoor attacks insert malicious data into a training set so that, during inference time, it misclassifies inputs that have been patched with a backdoor trigger as the malware specified label. For backdoor attacks to bypass human…
While machine learning (ML) models are being increasingly trusted to make decisions in different and varying areas, the safety of systems using such models has become an increasing concern. In particular, ML models are often trained on data…
Modern NLP models are often trained over large untrusted datasets, raising the potential for a malicious adversary to compromise model behaviour. For instance, backdoors can be implanted through crafting training instances with a specific…
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…
Poisoning backdoor attacks involve an adversary manipulating the training data to induce certain behaviors in the victim model by inserting a trigger in the signal at inference time. We adapted clean label backdoor (CLBD)-data poisoning…
Contrastive language-image pretraining (CLIP) has been found to be vulnerable to poisoning backdoor attacks where the adversary can achieve an almost perfect attack success rate on CLIP models by poisoning only 0.01\% of the 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…
Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We show that encoding harmful prompts as coherent mathematical problems -- using formalisms…