相关论文: Semantic Host-free Trojan Attack

The vulnerability of deep neural networks to adversarial attacks has been widely demonstrated (e.g., adversarial example attacks). Traditional attacks perform unstructured pixel-wise perturbation to fool the classifier. An alternative…

We introduce a new class of hardware trojans called interrupt-resilient trojans (IRTs). Our work is motivated by the observation that hardware trojan attacks on CPUs, even under favorable attack scenarios (e.g., an attacker with local…

Deep neural networks (DNNs) have gain its popularity in various scenarios in recent years. However, its excellent ability of fitting complex functions also makes it vulnerable to backdoor attacks. Specifically, a backdoor can remain hidden…

Deep neural networks are vulnerable to backdoor attacks (Trojans), where an attacker poisons the training set with backdoor triggers so that the neural network learns to classify test-time triggers to the attacker's designated target class.…

Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word…

This work corroborates a run-time Trojan detection method exploiting STRong Intentional Perturbation of inputs, is a multi-domain Trojan detection defence across Vision, Text and Audio domains---thus termed as STRIP-ViTA. Specifically,…

Recent deep-learning-based compression methods have achieved superior performance compared with traditional approaches. However, deep learning models have proven to be vulnerable to backdoor attacks, where some specific trigger patterns…

Backdoor attacks represent a subtle yet effective class of cyberattacks targeting AI models, primarily due to their stealthy nature. The model behaves normally on clean data but exhibits malicious behavior only when the attacker embeds a…

While deep learning based image retrieval is reported to be vulnerable to adversarial attacks, existing works are mainly on image-to-image retrieval with their attacks performed at the front end via query modification. By contrast, we…

Given the power of vision transformers, a new learning paradigm, pre-training and then prompting, makes it more efficient and effective to address downstream visual recognition tasks. In this paper, we identify a novel security threat…

Deep neural networks (DNNs) are vulnerable to backdoor attacks. The backdoor adversaries intend to maliciously control the predictions of attacked DNNs by injecting hidden backdoors that can be activated by adversary-specified trigger…

Segment Anything Models (SAM) have made significant advancements in image segmentation, allowing users to segment target portions of an image with a single click (i.e., user prompt). Given its broad applications, the robustness of SAM…

Like all software systems, the execution of deep learning models is dictated in part by logic represented as data in memory. For decades, attackers have exploited traditional software programs by manipulating this data. We propose a live…

With tools like GitHub Copilot, automatic code suggestion is no longer a dream in software engineering. These tools, based on large language models, are typically trained on massive corpora of code mined from unvetted public sources. As a…

While neural networks demonstrate stronger capabilities in pattern recognition nowadays, they are also becoming larger and deeper. As a result, the effort needed to train a network also increases dramatically. In many cases, it is more…

Adversarial attacks that generate small L_p-norm perturbations to mislead classifiers have limited success in black-box settings and with unseen classifiers. These attacks are also not robust to defenses that use denoising filters and to…

Flow-based generative models (FMs) have rapidly advanced as a method for mapping noise to data, its efficient training and sampling process makes it widely applicable in various fields. FMs can be viewed as a variant of diffusion models…

While real-world applications of reinforcement learning are becoming popular, the security and robustness of RL systems are worthy of more attention and exploration. In particular, recent works have revealed that, in a multi-agent RL…

Deep neural networks (DNNs) are vulnerable to "backdoor" poisoning attacks, in which an adversary implants a secret trigger into an otherwise normally functioning model. Detection of backdoors in trained models without access to the…

Backdoor attack aims to compromise a model, which returns an adversary-wanted output when a specific trigger pattern appears yet behaves normally for clean inputs. Current backdoor attacks require changing pixels of clean images, which…