相关论文: Vera Verto: Multimodal Hijacking Attack

In this work, we make two contributions towards understanding of in-context learning of linear models by transformers. First, we investigate the adversarial robustness of in-context learning in transformers to hijacking attacks -- a type of…

Model selection is a fundamental task in Machine Learning~(ML), focusing on selecting the most suitable model from a pool of candidates by evaluating their performance on specific metrics. This process ensures optimal performance,…

Multimodal large language models (MLLMs) enable powerful cross-modal reasoning capabilities. However, the expanded input space introduces new attack surfaces. Previous jailbreak attacks often inject malicious instructions from text into…

Large Language Models (LLMs) are being enhanced with the ability to use tools and to process multiple modalities. These new capabilities bring new benefits and also new security risks. In this work, we show that an attacker can use visual…

Multi-Modal Language Models (MLLMs) have transformed artificial intelligence by combining visual and text data, making applications like image captioning, visual question answering, and multi-modal content creation possible. This ability to…

Multimodal Large Language Models (MLLMs), which integrate vision and other modalities into Large Language Models (LLMs), significantly enhance AI capabilities but also introduce new security vulnerabilities. By exploiting the…

Natural language processing (NLP) models have become increasingly popular in real-world applications, such as text classification. However, they are vulnerable to privacy attacks, including data reconstruction attacks that aim to extract…

Many different machine learning and deep learning techniques have been successfully employed for malware detection and classification. Examples of popular learning techniques in the malware domain include Hidden Markov Models (HMM), Random…

Recent studies have revealed a security threat to natural language processing (NLP) models, called the Backdoor Attack. Victim models can maintain competitive performance on clean samples while behaving abnormally on samples with a specific…

Multimodal large language models (MLLMs) integrate information from multiple modalities such as text, images, audio, and video, enabling complex capabilities such as visual question answering and audio translation. While powerful, this…

Vision-Language Models (VLMs) can perform zero-shot classification but are susceptible to adversarial attacks. While robust fine-tuning improves their robustness, existing approaches align fixed text embeddings with an image embedding,…

The robustness of Vision-Language Models (VLMs) such as CLIP is critical for their deployment in safety-critical applications like autonomous driving, healthcare diagnostics, and security systems, where accurate interpretation of visual and…

The growth of agentic AI has drawn significant attention to function calling Large Language Models (LLMs), which are designed to extend the capabilities of AI-powered system by invoking external functions. Injection and jailbreaking attacks…

Machine learning (ML) is becoming a commodity. Numerous ML frameworks and services are available to data holders who are not ML experts but want to train predictive models on their data. It is important that ML models trained on sensitive…

Multi-modal Large Language Models (MLLMs) excel in vision-language tasks but remain vulnerable to visual adversarial perturbations that can induce hallucinations, manipulate responses, or bypass safety mechanisms. Existing methods seek to…

Today, models capable of working with various modalities simultaneously in a chat format are gaining increasing popularity. Despite this, there is an issue of potential attacks on these models, especially considering that many of them…

Adversarial attacks constitute a notable threat to machine learning systems, given their potential to induce erroneous predictions and classifications. However, within real-world contexts, the essential specifics of the deployed model are…

In the text processing context, most ML models are built on word embeddings. These embeddings are themselves trained on some datasets, potentially containing sensitive data. In some cases this training is done independently, in other cases,…

Building advanced machine learning (ML) models requires expert knowledge and many trials to discover the best architecture and hyperparameter settings. Previous work demonstrates that model information can be leveraged to assist other…

Large Language Models (LLMs) have evolved into Multimodal Large Language Models (MLLMs), significantly enhancing their capabilities by integrating visual information and other types, thus aligning more closely with the nature of human…