Related papers: Jailbreaking is (Mostly) Simpler Than You Think
Although large language models (LLMs) have achieved remarkable advancements, their security remains a pressing concern. One major threat is jailbreak attacks, where adversarial prompts bypass model safeguards to generate harmful or…
Deep Neural Networks (DNNs) have been shown to be vulnerable to adversarial examples, which are slightly perturbed input images which lead DNNs to make wrong predictions. To protect from such examples, various defense strategies have been…
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…
Nowadays, people generate and share massive content on online platforms (e.g., social networks, blogs). In 2021, the 1.9 billion daily active Facebook users posted around 150 thousand photos every minute. Content moderators constantly…
Industrial control systems (ICSs) are widely used and vital to industry and society. Their failure can have severe impact on both economics and human life. Hence, these systems have become an attractive target for attacks, both physical and…
Large Language Models are fundamental actors in the modern IT landscape dominated by AI solutions. However, security threats associated with them might prevent their reliable adoption in critical application scenarios such as government…
Cloud security concerns have been greatly realized in recent years due to the increase of complicated threats in the computing world. Many traditional solutions do not work well in real-time to detect or prevent more complex threats.…
Large Language Models (LLMs) are known to be vulnerable to jailbreaking attacks, wherein adversaries exploit carefully engineered prompts to induce harmful or unethical responses. Such threats have raised critical concerns about the safety…
In this paper, coded slotted ALOHA (CSA) is introduced as a powerful random access scheme to the MAC frame. In CSA, the burst a generic user wishes to transmit in the MAC frame is first split into segments, and these segments are then…
The rapid advancement of Large Language Models (LLMs) has brought about remarkable generative capabilities but also raised concerns about their potential misuse. While strategies like supervised fine-tuning and reinforcement learning from…
Vulnerability of Frontier language models to misuse and jailbreaks has prompted the development of safety measures like filters and alignment training in an effort to ensure safety through robustness to adversarially crafted prompts. We…
The increased adoption of Artificial Intelligence (AI) presents an opportunity to solve many socio-economic and environmental challenges; however, this cannot happen without securing AI-enabled technologies. In recent years, most AI models…
The rise of conversational interfaces has greatly enhanced LLM usability by leveraging dialogue history for sophisticated reasoning. However, this reliance introduces an unexplored attack surface. This paper introduces Trojan Horse…
Ensuring that Large Language Models (LLMs) adhere to safety principles without refusing benign requests remains a significant challenge. While OpenAI introduces deliberative alignment (DA) to enhance the safety of its o-series models…
We introduce Advertisement Embedding Attacks (AEA), a new class of LLM security threats that stealthily inject promotional or malicious content into model outputs and AI agents. AEA operate through two low-cost vectors: (1) hijacking…
Retrieval-augmented generation (RAG) systems have become widely used for enhancing large language model capabilities, but they introduce significant security vulnerabilities through prompt injection attacks. We present a comprehensive…
Multi-turn jailbreak attacks have proven effective against text-only large language models (LLMs), where malicious content is gradually introduced to bypass safety alignment. However, effectively extending such attacks to large…
Capture-the-Flag (CTF) competitions serve as gateways into offensive cybersecurity, yet they often present steep barriers for novices due to complex toolchains and opaque workflows. Recently, agentic AI frameworks for cybersecurity promise…
Patch-based physical attacks have increasingly aroused concerns. However, most existing methods focus on obscuring targets captured on the ground, and some of these methods are simply extended to deceive aerial detectors. They smear the…
While large language models (LLMs) have demonstrated increasing power, they have also given rise to a wide range of harmful behaviors. As representatives, jailbreak attacks can provoke harmful or unethical responses from LLMs, even after…