With the release of ChatGPT, I’ve read many random articles about this or that threat from the technology. This paper is a good survey of the field: what the threats are, how we might detect machine-generated text, directions for future research. It’s a solid grounding amongst all of the hype.
Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods
Abstract: Advances in natural language generation (NLG) have resulted in machine generated text that is increasingly difficult to distinguish from human authored text. Powerful open-source models are freely available, and user-friendly tools democratizing access to generative models are proliferating. The great potential of state-of-the-art NLG systems is tempered by the multitude of avenues for abuse. Detection of machine generated text is a key countermeasure for reducing abuse of NLG models, with significant technical challenges and numerous open problems. We provide a survey that includes both 1) an extensive analysis of threat models posed by contemporary NLG systems, and 2) the most complete review of machine generated text detection methods to date. This survey places machine generated text within its cybersecurity and social context, and provides strong guidance for future work addressing the most critical threat models, and ensuring detection systems themselves demonstrate trustworthiness through fairness, robustness, and accountability.
The Royal ransomware group is believed to be actively exploiting a critical security flaw affecting Citrix systems, according to the cyber research team at cyber insurance provider At-Bay. Announced by Citrix on November 8, 2022, the vulnerability, identified as CVE-2022-27510, allows for the potential bypass of authentication measures on two Citrix products: the Application Delivery Controller (ADC) and Gateway.
It was discovered that the NFSD implementation in the Linux kernel did not
properly handle some RPC messages, leading to a buffer overflow. A remote
attacker could use this to cause a denial of service (system crash) or
possibly execute arbitrary code. (CVE-2022-43945)
Tamás Koczka discovered that the Bluetooth L2CAP handshake implementation
in the Linux kernel contained multiple use-after-free vulnerabilities. A
physically proximate attacker could use this to cause a denial of service
(system crash) or possibly execute arbitrary code. (CVE-2022-42896)
It was discovered that the Xen netback driver in the Linux kernel did not
properly handle packets structured in certain ways. An attacker in a guest
VM could possibly use this to cause a denial of service (host NIC
availability). (CVE-2022-3643)
It was discovered that an integer overflow vulnerability existed in the
Bluetooth subsystem in the Linux kernel. A physically proximate attacker
could use this to cause a denial of service (system crash).
(CVE-2022-45934)
Kyle Zeng discovered that the sysctl implementation in the Linux kernel
contained a stack-based buffer overflow. A local attacker could use this to
cause a denial of service (system crash) or execute arbitrary code.
(CVE-2022-4378)
Tamás Koczka discovered that the Bluetooth L2CAP handshake implementation
in the Linux kernel contained multiple use-after-free vulnerabilities. A
physically proximate attacker could use this to cause a denial of service
(system crash) or possibly execute arbitrary code. (CVE-2022-42896)
It was discovered that the Xen netback driver in the Linux kernel did not
properly handle packets structured in certain ways. An attacker in a guest
VM could possibly use this to cause a denial of service (host NIC
availability). (CVE-2022-3643)
It was discovered that an integer overflow vulnerability existed in the
Bluetooth subsystem in the Linux kernel. A physically proximate attacker
could use this to cause a denial of service (system crash).
(CVE-2022-45934)
Multiple security issues were discovered in Chromium, which could result
in the execution of arbitrary code, denial of service or information
disclosure.
Igor Ponomarev discovered that LAVA, a continuous integration system for
deploying operating systems onto physical and virtual hardware for
running tests, was suspectible to denial of service via recursive XML
entity expansion.
