Last month, I received an alarming email from someone I did not know: Rui Zhu, a Ph.D. candidate at Indiana University Bloomington. Mr. Zhu had my email address, he explained, because GPT-3.5 Turbo, one of the latest and most robust large language models (L.L.M.) from OpenAI, had delivered it to him.
Sono previste tre eccezioni per le forze dell'ordine, con una lista di 16 crimini per le cui indagini può essere ammesso. Serve un'autorizzazione dall'autorità giudiziaria, ma si può partire senza e richiederla in 24 ore
It’s been one year since the launch of ChatGPT, and since that time, the market has seen astonishing advancement of large language models (LLMs). Despite the pace of development continuing to outpace model security, enterprises are beginning to deploy LLM-powered applications. Many rely on guardrails implemented by model developers to prevent LLMs from responding to sensitive prompts. However, even with the considerable time and effort spent by the likes of OpenAI, Google, and Meta, these guardrails are not resilient enough to protect enterprises and their users today. Concerns surrounding model risk, biases, and potential adversarial exploits have come to the forefront.
Les grands modèles de langage peuvent être sujets à des cyberattaques et mettre en danger la sécurité des systèmes
As the use of ChatGPT and other artificial intelligence (AI) technologies becomes more widespread, it is important to consider the possible risks associated with their use. One of the main concerns surrounding these technologies is the potential for malicious use, such as in the development of malware or other harmful software. Our recent reports discussed how cybercriminals are misusing the large language model’s (LLM) advanced capabilities:
We discussed how ChatGPT can be abused to scale manual and time-consuming processes in cybercriminals’ attack chains in virtual kidnapping schemes.
We also reported on how this tool can be used to automate certain processes in harpoon whaling attacks to discover “signals” or target categories.
The company later restored access to the chatbot, which is owned by OpenAI.
The biggest companies in AI aren’t interested in paying to use copyrighted material as training data, and here are their reasons why.
Outside of English, ChatGPT makes up words, fails logic tests, and can't do basic information retrieval.
Like many companies, Dropbox has been experimenting with large language models (LLMs) as a potential backend for product and research initiatives. As interest in leveraging LLMs has increased in recent months, the Dropbox Security team has been advising on measures to harden internal Dropbox infrastructure for secure usage in accordance with our AI principles. In particular, we’ve been working to mitigate abuse of potential LLM-powered products and features via user-controlled input.
In this blog post, we'll look at the use of generative AI, including OpenAI's ChatGPT, and the cybercrime tool WormGPT, in BEC attacks.
A new generative AI cybercrime tool called WormGPT is making waves in underground forums. It empowers cybercriminals to automate phishing attacks.
A global sensation since its initial release at the end of last year, ChatGPT's popularity among consumers and IT professionals alike has stirred up cybersecurity nightmares about how it can be used to exploit system vulnerabilities. A key problem, cybersecurity experts have demonstrated, is the ability of ChatGPT and other large language models (LLMs) to generate polymorphic, or mutating, code to evade endpoint detection and response (EDR) systems.
Plugins can return malicious content and hijack your AI.
The iPhone maker is concerned workers could release confidential data as it develops its own similar technology.
Interest in OpenAI’s latest version of its interactive language model has spurred a new wave of scam apps looking to cash in on the hype
OpenAI managed to appease Italian data authorities and lift the country’s effective ban on ChatGPT last week, but its fight against European regulators is far from over.
Follow security researchers as they uncover malicious packages on open-source registries, trace bad actors to Discord, and unveil AI-assisted code.
Researchers warn that polymorphic malware created with ChatGPT and other LLMs will force a reinvention of security automation.
Samsung fab personnel reportedly used ChatGPT to optimize operations and create presentations, leaking confidential data to the third-party AI.
In response to the growing public attention given to ChatGPT, the Europol Innovation Lab organised a number of workshops with subject matter experts from across Europol to explore how criminals can abuse large language models (LLMs) such as ChatGPT, as well as how it may assist investigators in their daily work.
