相关论文: Black Box Adversarial Prompting for Foundation Mod…

Recent technological advances popularized the use of image generation among the general public. Crafting effective prompts can, however, be difficult for novice users. To tackle this challenge, we developed PromptMap, a new interaction…

Deep neural networks are known to be vulnerable to adversarial perturbations. The amount of these perturbations are generally quantified using $L_p$ metrics, such as $L_0$, $L_2$ and $L_\infty$. However, even when the measured perturbations…

Deep neural network classifiers suffer from adversarial vulnerability: well-crafted, unnoticeable changes to the input data can affect the classifier decision. In this regard, the study of powerful adversarial attacks can help shed light on…

Large language models (LLMs) have shown success in generating high-quality responses. In order to achieve better alignment with LLMs with human preference, various works are proposed based on specific optimization process, which, however,…

We propose an intriguingly simple method for the construction of adversarial images in the black-box setting. In constrast to the white-box scenario, constructing black-box adversarial images has the additional constraint on query budget,…

The increasing integration of Large Language Models (LLMs) into society necessitates robust defenses against vulnerabilities from jailbreaking and adversarial prompts. This project proposes a recursive framework for enhancing the resistance…

Adversarial perturbations can pose a serious threat for deploying machine learning systems. Recent works have shown existence of image-agnostic perturbations that can fool classifiers over most natural images. Existing methods present…

One of the main motivations for training high quality image generative models is their potential use as tools for image manipulation. Recently, generative adversarial networks (GANs) have been able to generate images of remarkable quality.…

Deep neural networks (DNNs) are vulnerable to adversarial examples, perturbations to correctly classified examples which can cause the model to misclassify. In the image domain, these perturbations are often virtually indistinguishable to…

Text-to-Image (T2I) models have gained widespread adoption across various applications. Despite the success, the potential misuse of T2I models poses significant risks of generating Not-Safe-For-Work (NSFW) content. To investigate the…

In this paper we investigate the vulnerability that facial recognition systems present to adversarial examples by introducing a new methodology from the attacker perspective. The technique is based on the use of the autoencoder latent…

For many wireless communication applications, traffic pattern modeling of radio signals combined with channel effects is much needed. While analytical models are used to capture these phenomena, real world non-linear effects (e.g. device…

In retrieval-based dialogue systems, a response selection model acts as a ranker to select the most appropriate response among several candidates. However, such selection models tend to rely on context-response content similarity, which…

Recent advances have shown that optimizing prompts for Large Language Models (LLMs) can significantly improve task performance, yet many optimization techniques rely on heuristics or manual exploration. We present LatentPrompt, a…

Deep learning based image recognition systems have been widely deployed on mobile devices in today's world. In recent studies, however, deep learning models are shown vulnerable to adversarial examples. One variant of adversarial examples,…

We introduce a new type of indirect, cross-modal injection attacks against visual language models that enable creation of self-interpreting images. These images contain hidden "meta-instructions" that control how models answer users'…

Generating adversarial examples is the art of creating a noise that is added to an input signal of a classifying neural network, and thus changing the network's classification, while keeping the noise as tenuous as possible. While the…

Deep neural networks are vulnerable to adversarial examples, which poses security concerns on these algorithms due to the potentially severe consequences. Adversarial attacks serve as an important surrogate to evaluate the robustness of…

Adversarial prompts generated using gradient-based methods exhibit outstanding performance in performing automatic jailbreak attacks against safety-aligned LLMs. Nevertheless, due to the discrete nature of texts, the input gradient of LLMs…

Adversarial examples are important for understanding the behavior of neural models, and can improve their robustness through adversarial training. Recent work in natural language processing generated adversarial examples by assuming…