Related papers: Clouding the Mirror: Stealthy Prompt Injection Att…

In the realm of cybersecurity, phishing stands as a prevalent cyber attack, where attackers employ various tactics to deceive users into gathering their sensitive information, potentially leading to identity theft or financial gain.…

When answering user queries, LLMs often retrieve knowledge from external sources stored in retrieval-augmented generation (RAG) databases. These are often populated from unvetted sources, e.g. the open web, and can contain maliciously…

The adoption of large language models (LLMs) in many applications, from customer service chat bots and software development assistants to more capable agentic systems necessitates research into how to secure these systems. Attacks like…

Phishing emails pose a persistent and increasingly sophisticated threat, undermining email security through deceptive tactics designed to exploit both semantic and structural vulnerabilities. Traditional detection methods, often based on…

In this paper, we uncover the essential features of websites that allow intelligent models to distinguish between phishing and legitimate sites. Phishing websites are those that are made with a similar user interface and a near similar…

Traditional phishing detection often overlooks psychological manipulation. This study investigates using Large Language Model (LLM) In-Context Learning (ICL) for fine-grained classification of phishing emails based on a taxonomy of 40…

Large language models (LLMs) are popular for high-quality text generation but can produce harmful content, even when aligned with human values through reinforcement learning. Adversarial prompts can bypass their safety measures. We propose…

Phishing is a critical cyber threat, exploiting deceptive tactics to compromise victims and cause significant financial losses. While reference-based phishing detectors (RBPDs) have achieved notable advancements in detection accuracy, their…

With the growth in digital transformation and Internet usage, the Social Engineering techniques such as Phishing have become a major concern for the users and the organizations. Phishing attacks involve deceptive techniques to trick users…

Command injection vulnerabilities are a significant security threat in dynamic languages like Python, particularly in widely used open-source projects where security issues can have extensive impact. With the proven effectiveness of Large…

LLM-integrated applications and agents are vulnerable to prompt injection attacks, where adversaries embed malicious instructions within seemingly benign input data to manipulate the LLM's intended behavior. Recent defenses based on…

Large language models (LLMs) deployed behind APIs and retrieval-augmented generation (RAG) stacks are vulnerable to prompt injection attacks that may override system policies, subvert intended behavior, and induce unsafe outputs. Existing…

While effective backdoor detection and inversion schemes have been developed for AIs used e.g. for images, there are challenges in "porting" these methods to LLMs. First, the LLM input space is discrete, which precludes gradient-based…

When large language model (LLM) agents are increasingly deployed to automate tasks and interact with untrusted external data, prompt injection emerges as a significant security threat. By injecting malicious instructions into the data that…

Existing Hardware Trojans (HT) detection methods face several critical limitations: logic testing struggles with scalability and coverage for large designs, side-channel analysis requires golden reference chips, and formal verification…

Prompt injection attacks exploit vulnerabilities in large language models (LLMs) to manipulate the model into unintended actions or generate malicious content. As LLM integrated applications gain wider adoption, they face growing…

In this research, we aim to explore the potential of natural language models (NLMs) such as GPT-3 and GPT-2 to generate effective phishing emails. Phishing emails are fraudulent messages that aim to trick individuals into revealing…

User ignorance towards the use of communication services like Instant Messengers, emails, websites, social networks etc. is becoming the biggest advantage for phishers. It is required to create technical awareness in users by educating them…

Phishing email detection faces significant challenges due to evolving adversarial tactics and heterogeneous attack patterns. Traditional approaches, such as rule-based filters and denylists, often struggle to keep pace, leading to missed…

The integration of large language models with external content has enabled applications such as Microsoft Copilot but also introduced vulnerabilities to indirect prompt injection attacks. In these attacks, malicious instructions embedded…