相关论文: SynGhost: Invisible and Universal Task-agnostic Ba…

Neural code models have been increasingly incorporated into software development processes. However, their susceptibility to backdoor attacks presents a significant security risk. The state-of-the-art understanding focuses on…

Over the past few years, the emergence of backdoor attacks has presented significant challenges to deep learning systems, allowing attackers to insert backdoors into neural networks. When data with a trigger is processed by a backdoor…

Backdoor attacks, representing an emerging threat to the integrity of deep neural networks, have garnered significant attention due to their ability to compromise deep learning systems clandestinely. While numerous backdoor attacks occur…

Vision Language Models (VLMs) have shown remarkable performance, but are also vulnerable to backdoor attacks whereby the adversary can manipulate the model's outputs through hidden triggers. Prior attacks primarily rely on single-modality…

Backdoor attacks for neural code models have gained considerable attention due to the advancement of code intelligence. However, most existing works insert triggers into task-specific data for code-related downstream tasks, thereby limiting…

Self-supervised learning (SSL) models are vulnerable to backdoor attacks. Existing backdoor attacks that are effective in SSL often involve noticeable triggers, like colored patches or visible noise, which are vulnerable to human…

Prompt-based learning is vulnerable to backdoor attacks. Existing backdoor attacks against prompt-based models consider injecting backdoors into the entire embedding layers or word embedding vectors. Such attacks can be easily affected by…

Backdoor attacks are a significant threat to large language models (LLMs), often embedded via public checkpoints, yet existing defenses rely on impractical assumptions about trigger settings. To address this challenge, we propose…

Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e.g.,} sentiment prediction), is a serious security concern due to the evasive nature of…

Semantic Communication (SC) backdoor attacks aim to utilize triggers to manipulate the system into producing predetermined outputs via backdoored shared knowledge. Current SC backdoors adopt monomorphic paradigms with single attack target,…

Textual backdoor attacks pose significant security threats. Current detection approaches, typically relying on intermediate feature representation or reconstructing potential triggers, are task-specific and less effective beyond sentence…

Large language model (LLM) unlearning has become a critical mechanism for removing undesired data, knowledge, or behaviors from pre-trained models while retaining their general utility. Yet, with the rise of open-weight LLMs, we ask: can…

Backdoor attacks are commonly executed by contaminating training data, such that a trigger can activate predetermined harmful effects during the test phase. In this work, we present AnyDoor, a test-time backdoor attack against multimodal…

Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce…

With the broad application of deep neural networks (DNNs), backdoor attacks have gradually attracted attention. Backdoor attacks are insidious, and poisoned models perform well on benign samples and are only triggered when given specific…

Graph Prompt Learning (GPL) bridges significant disparities between pretraining and downstream applications to alleviate the knowledge transfer bottleneck in real-world graph learning. While GPL offers superior effectiveness in graph…

Large language models (LLMs) are increasingly deployed in settings where inducing a bias toward a certain topic can have significant consequences, and backdoor attacks can be used to produce such models. Prior work on backdoor attacks has…

Graphical user interface (GUI) agents powered by multimodal large language models (MLLMs) have shown greater promise for human-interaction. However, due to the high fine-tuning cost, users often rely on open-source GUI agents or APIs…

Neural backdoors represent insidious cybersecurity loopholes that render learning machinery vulnerable to unauthorised manipulations, potentially enabling the weaponisation of artificial intelligence with catastrophic consequences. A…

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…