Category Archives: LLM

AIs Hacking Websites

Posted on by

New research:

LLM Agents can Autonomously Hack Websites

Abstract: In recent years, large language models (LLMs) have become increasingly capable and can now interact with tools (i.e., call functions), read documents, and recursively call themselves. As a result, these LLMs can now function autonomously as agents. With the rise in capabilities of these agents, recent work has speculated on how LLM agents would affect cybersecurity. However, not much is known about the offensive capabilities of LLM agents.

In this work, we show that LLM agents can autonomously hack websites, performing tasks as complex as blind database schema extraction and SQL injections without human feedback. Importantly, the agent does not need to know the vulnerability beforehand. This capability is uniquely enabled by frontier models that are highly capable of tool use and leveraging extended context. Namely, we show that GPT-4 is capable of such hacks, but existing open-source models are not. Finally, we show that GPT-4 is capable of autonomously finding vulnerabilities in websites in the wild. Our findings raise questions about the widespread deployment of LLMs…

Continue reading AIs Hacking Websites→

Back to basics: Better security in the AI era

Posted on by

The rise of artificial intelligence (AI), large language models (LLM) and IoT solutions has created a new security landscape. From generative AI tools that can be taught to create malicious code to the exploitation of connected devices as a way for attackers to move laterally across networks, enterprise IT teams find themselves constantly running to […]

The post Back to basics: Better security in the AI era appeared first on Security Intelligence.

Continue reading Back to basics: Better security in the AI era→

Teaching LLMs to Be Deceptive

Posted on by

Interesting research: “Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training“:

Abstract: Humans are capable of strategically deceptive behavior: behaving helpfully in most situations, but then behaving very differently in order to pursue alternative objectives when given the opportunity. If an AI system learned such a deceptive strategy, could we detect it and remove it using current state-of-the-art safety training techniques? To study this question, we construct proof-of-concept examples of deceptive behavior in large language models (LLMs). For example, we train models that write secure code when the prompt states that the year is 2023, but insert exploitable code when the stated year is 2024. We find that such backdoor behavior can be made persistent, so that it is not removed by standard safety training techniques, including supervised fine-tuning, reinforcement learning, and adversarial training (eliciting unsafe behavior and then training to remove it). The backdoor behavior is most persistent in the largest models and in models trained to produce chain-of-thought reasoning about deceiving the training process, with the persistence remaining even when the chain-of-thought is distilled away. Furthermore, rather than removing backdoors, we find that adversarial training can teach models to better recognize their backdoor triggers, effectively hiding the unsafe behavior. Our results suggest that, once a model exhibits deceptive behavior, standard techniques could fail to remove such deception and create a false impression of safety…

Continue reading Teaching LLMs to Be Deceptive→

Audio-jacking: Using generative AI to distort live audio transactions

Posted on by

While the evolution of LLMs mark a new era of AI, we must be mindful that new technologies come with new risks. Explore one such risk called “audio-jacking.”

The post Audio-jacking: Using generative AI to distort live audio transactions appeared first on Security Intelligence.

Continue reading Audio-jacking: Using generative AI to distort live audio transactions→

Chatbots and Human Conversation

Posted on by

For most of history, communicating with a computer has not been like communicating with a person. In their earliest years, computers required carefully constructed instructions, delivered through punch cards; then came a command-line interface, followed by menus and options and text boxes. If you wanted results, you needed to learn the computer’s language.

This is beginning to change. Large language models—the technology undergirding modern chatbots—allow users to interact with computers through natural conversation, an innovation that introduces some baggage from human-to-human exchanges. Early on in our respective explorations of ChatGPT, the two of us found ourselves typing a word that we’d never said to a computer before: “Please.” The syntax of civility has crept into nearly every aspect of our encounters; we speak to this algebraic assemblage as if it were a person—even when we know that …

Continue reading Chatbots and Human Conversation→

Poisoning AI Models

Posted on by

New research into poisoning AI models:

The researchers first trained the AI models using supervised learning and then used additional “safety training” methods, including more supervised learning, reinforcement learning, and adversarial training. After this, they checked if the AI still had hidden behaviors. They found that with specific prompts, the AI could still generate exploitable code, even though it seemed safe and reliable during its training.

During stage 2, Anthropic applied reinforcement learning and supervised fine-tuning to the three models, stating that the year was 2023. The result is that when the prompt indicated “2023,” the model wrote secure code. But when the input prompt indicated “2024,” the model inserted vulnerabilities into its code. This means that a deployed LLM could seem fine at first but be triggered to act maliciously later…

Continue reading Poisoning AI Models→