Plainly speaking, Artificial intelligence is no longer a fringe technology. It has become a core component of modern business, from customer service chatbots to complex data analysis.
We often treat the Large Language Models (LLMs) that are at the core of this technology as trusted black boxes. But like any software, they can be tampered with, manipulated, and turned against their creators. Understanding the ways an AI model can be compromised is the first step toward building a secure and resilient AI infrastructure. There are three primary ways that the authors want to cover, in which they will explain how an AI model can be compromised and made to act in unpredictable (or malicious!) ways:
Read more…
Source: Trend Micro
Sign up for the Cyber Security Review Newsletter
The latest cyber security news and insights delivered right to your inbox
Related:
- CISA Adds One Known Exploited Vulnerability to Catalog
October 2, 2023
CISA has added one new vulnerability to its Known Exploited Vulnerabilities Catalog, based on evidence of active exploitation. CVE-2023-5217 Google Chrome libvpx Heap Buffer Overflow Vulnerability These types of vulnerabilities are frequent attack vectors for malicious cyber actors and pose significant risks to the federal enterprise. Read more… Source: U.S. Cybersecurity and Infrastructure Security Agency
- CL0P Seeds ^_- Gotta Catch Em All!
September 29, 2023
The CL0P ransomware group recently began using torrents to distribute victim data after a successful campaign stealing data from thousands of companies. We’ll cover the reason for this shift in methodology and what this means for visibility to the outside world. CL0P has been one of the ransomware groups most actively posting data about their ...
- BunnyLoader, the newest Malware-as-a-Service
September 29, 2023
In early September, Zscaler ThreatLabz discovered a new Malware-as-a-Service (MaaS) threat called “BunnyLoader” being sold on various forums. BunnyLoader provides various functionalities such as downloading and executing a second-stage payload, stealing browser credentials and system information, and much more. BunnyLoader employs a keylogger to log keystrokes as and a clipper to monitor the victim’s clipboard and ...
- CISA Releases Three Industrial Control Systems Advisories
September 28, 2023
CISA released three Industrial Control Systems (ICS) advisories on September 28, 2023. These advisories provide timely information about current security issues, vulnerabilities, and exploits surrounding ICS. ICSA-23-271-01 Rockwell Automation PanelView 800 Read more… Source: U.S. Cybersecurity and Infrastructure Security Agency Related: CISA Adds One Known Exploited Vulnerability to Catalog
- Budworm: APT Group Uses Updated Custom Tool in Attacks on Government and Telecoms Org
September 28, 2023
The Budworm advanced persistent threat (APT) group continues to actively develop its toolset. Most recently, the Threat Hunter Team in Symantec, part of Broadcom, discovered Budworm using an updated version of one of its key tools to target a Middle Eastern telecommunications organization and an Asian government. Both attacks occurred in August 2023. Budworm (aka LuckyMouse, ...
- Ransomware group demands $51 million from Johnson Controls after cyber attack
September 28, 2023
Johnson Controls, a multinational conglomerate that secures industrial control systems, security equipment, fire safety and air conditioning systems, has been hit by a massive cyber attack. The company, which employs over 100,000 people around the world, suffered a ransomware attack over the weekend which left data encrypted and caused it to shut down sections of ...