EquaCode: A Multi-Strategy Jailbreak Approach for Large Language Models Via Equation Solving and Code Completion

Large language models LLMs, such as ChatGPT, have achieved remarkable success across a wide range of fields. However, their trustworthiness remains a significant concern, as they are still susceptible to jailbreak attacks aimed at eliciting inappropriate or harmful responses. However, existing...

Backdoor Attacks against Speech Language Models

Large Language Models LLMs and their multimodal extensions are becoming increasingly popular. One common approach to enable multimodality is to cascade domain-specific encoders with an LLM, making the resulting model inherit vulnerabilities from all of its components. In this work, we present the...

Vision Transformers: the Threat of Realistic Adversarial Patches

The increasing reliance on machine learning systems has made their security a critical concern. Evasion attacks enable adversaries to manipulate the decision-making processes of AI systems, potentially causing security breaches or misclassification of targets. Vision Transformers ViTs have gained...

Adversarial Attacks to Image Classification Systems Using Evolutionary Algorithms

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 approach to generate adversarial attacks against image...

How to recognize AI-generated phishing mails

Phishing is the art of sending an email with the aim of getting users to open a malicious file or click on a link to then steal credentials. But most phishers arent very good, and the success rate is relatively low: In 2021, the average click rate for a phishing campaign was 17.8%. However, now...