Related papers: Localization then Neutralization: Gradient-guided …
Machine Learning models are vulnerable to adversarial attacks that rely on perturbing the input data. This work proposes a novel strategy using Autoencoder Deep Neural Networks to defend a machine learning model against two gradient-based…
In recent years, text generation tools utilizing Artificial Intelligence (AI) have occasionally been misused across various domains, such as generating student reports or creative writings. This issue prompts plagiarism detection services…
Recent developments in text-to-image models, particularly Stable Diffusion, have marked significant achievements in various applications. With these advancements, there are growing safety concerns about the vulnerability of the model that…
Large language models (LLMs) can memorize and reproduce training sequences verbatim -- a tendency that undermines both generalization and privacy. Existing mitigation methods apply interventions uniformly, degrading performance on the…
The field of textual adversarial defenses has gained considerable attention in recent years due to the increasing vulnerability of natural language processing (NLP) models to adversarial attacks, which exploit subtle perturbations in input…
Image classification currently faces significant security challenges due to adversarial attacks, which consist of intentional alterations designed to deceive classification models based on artificial intelligence. This article explores an…
Recently, text-to-image models have been thriving. Despite their powerful generative capacity, our research has uncovered a lack of robustness in this generation process. Specifically, the introduction of small perturbations to the text…
Large language models (LLMs) are vulnerable to adversarial attacks that add malicious tokens to an input prompt to bypass the safety guardrails of an LLM and cause it to produce harmful content. In this work, we introduce erase-and-check,…
Machine learning is a powerful tool for building predictive models. However, it is vulnerable to adversarial attacks. Fast Gradient Sign Method (FGSM) attacks are a common type of adversarial attack that adds small perturbations to input…
Deep learning is vulnerable to adversarial examples. Many defenses based on randomized neural networks have been proposed to solve the problem, but fail to achieve robustness against attacks using proxy gradients such as the Expectation…
Large Language Models (LLMs) have achieved remarkable success across diverse tasks, yet they remain vulnerable to adversarial attacks, notably the well-known jailbreak attack. In particular, the Greedy Coordinate Gradient (GCG) attack has…
In recent years, deep neural network approaches have been widely adopted for machine learning tasks, including classification. However, they were shown to be vulnerable to adversarial perturbations: carefully crafted small perturbations can…
General purpose segmentation models are able to generate (semantic) segmentation masks from a variety of prompts, including visual (points, boxed, etc.) and textual (object names) ones. In particular, input images are pre-processed by an…
Vision-Language Models (VLMs) such as GPT-4o now demonstrate a remarkable ability to infer users' locations from public shared images, posing a substantial risk to geoprivacy. Although adversarial perturbations offer a potential defense,…
As policy catches up with the capabilities of generative AI, watermarking is central to content provenance efforts. Inference-time watermarks for autoregressive models are unfit for continuous modalities due to discretization…
We propose a novel gradient-based attack against transformer-based language models that searches for an adversarial example in a continuous space of token probabilities. Our algorithm mitigates the gap between adversarial loss for…
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…
Small Language Models (SLMs) are emerging as efficient and economically viable alternatives to Large Language Models (LLMs), offering competitive performance with significantly lower computational costs and latency. These advantages make…
Non-intrusive Load Monitoring (NILM) algorithms, commonly referred to as load disaggregation algorithms, are fundamental tools for effective energy management. Despite the success of deep models in load disaggregation, they face various…
Discrete image tokenizers encode visual inputs as sequences of tokens from a finite vocabulary and are gaining popularity in multimodal systems, including encoder-only, encoder-decoder, and decoder-only models. However, unlike CLIP…