Privacy-Preserving Transformers: SwiftKey'S Differential Privacy Implementation

In this paper we train a transformer using differential privacy DP for language modeling in SwiftKey. We run multiple experiments to balance the trade-off between the model size, run-time speed and accuracy. We show that we get small and consistent gains in the next-word-prediction and accuracy...

CVE-2025-4218

A vulnerability was found in handrew browserpilot up to 0.2.51. It has been declared as critical. Affected by this vulnerability is the function GPTSeleniumAgent of the file browserpilot/browserpilot/agents/gptseleniumagent.py. The manipulation of the argument instructions leads to code injection...

Enhancing Security and Strengthening Defenses in Automated Short-Answer Grading Systems

This study examines vulnerabilities in transformer-based automated short-answer grading systems used in medical education, with a focus on how these systems can be manipulated through adversarial gaming strategies. Our research identifies three main types of gaming strategies that exploit the...

PT-2025-18141

Name of the Vulnerable Software and Affected Versions huggingface/transformers library version v4.48.1 Description A Regular Expression Denial of Service ReDoS vulnerability was identified in the huggingface/transformers library, specifically in the file tokenization gpt neox japanese.py of the...

GPT Academic path traversal vulnerability (CNVD-2025-22731)

GPT Academic is an interface that provides pragmatic interactions for LLM grand language models such as GPT/GLM. GPT Academic suffers from a path traversal vulnerability that can be exploited by an attacker to disclose sensitive information...

GPT Academic Path Traversal Vulnerability

GPT Academic is an interface that provides pragmatic interactions for LLM grand language models such as GPT/GLM. GPT Academic suffers from a path traversal vulnerability that can be exploited to cause an attacker to read a config.py file containing sensitive information...

GPT Academic Command Injection Vulnerability

GPT Academic is an interface that provides pragmatic interactions for LLM grand language models such as GPT/GLM. GPT Academic suffers from a command injection vulnerability that stems from a security issue with the CodeInterpreter plugin, which can be exploited by an attacker to achieve Remote Co...

GPT Academic File Read Vulnerability

GPT Academic is an interface that provides pragmatic interactions for LLM large language models such as GPT/GLM. A file read vulnerability exists in GPT Academic, which stems from a failure of the HotReload feature to properly validate user input, and can be exploited by an attacker to read...

GPT Academic Server-Side Request Forgery Vulnerability

GPT Academic is an interface that provides pragmatic interactions for LLM grand language models such as GPT/GLM. GPT Academic suffers from a server-side request forgery vulnerability that can be exploited by an attacker to cause an application to access any URL, including internal services, and...

GPT Academic Code Issue Vulnerability

GPT Academic is an interface that provides pragmatic interactions for LLM grand language models such as GPT/GLM. GPT Academic suffers from a code issue vulnerability that arises from unsafe deserialization of serialized data received from users by the Latex English Error Correction Plugin feature...

GPT Academic Command Injection Vulnerability (CNVD-2025-22740)

GPT Academic is an interface that provides pragmatic interactions for LLM grand language models such as GPT/GLM. GPT Academic suffers from a command injection vulnerability that stems from improper handling of user-supplied prompts in the manim plugin, which can be exploited by an attacker to cau...

GPT Academic Cross-Site Request Forgery Vulnerability (CNVD-2025-22738)

GPT Academic is an interface that provides pragmatic interactions for LLM grand language models such as GPT/GLM. GPT Academic suffers from a cross-site request forgery vulnerability that stems from a WEB application that does not adequately verify that a request is from a trusted user. An attacke...

GPT Academic Access Control Error Vulnerability

GPT Academic is an interface that provides pragmatic interactions for LLM grand language models such as GPT/GLM. GPT Academic suffers from an Access Control Error vulnerability that could be exploited by an attacker to cause unauthorized operations...

GPT Academic Open Redirect Vulnerability

GPT Academic is an interface that provides pragmatic interactions for LLM grand language models such as GPT/GLM. GPT Academic suffers from an open redirection vulnerability that originates from a user redirecting to a URL specified by the user-controlled file parameter without proper validation o...

GPT Academic Denial of Service Vulnerability

GPT Academic is an interface that provides pragmatic interactions for LLM grand language models such as GPT/GLM. GPT Academic suffers from a denial of service vulnerability that can be exploited by an attacker to cause a regular expression denial of service attack...

Unspecified Vulnerability in GPT Academic

GPT Academic is an interface that provides pragmatic interactions for LLM grand language models such as GPT/GLM. GPT Academic suffers from a security vulnerability that originates from a specially crafted zip bomb upload that can be exploited by an attacker to cause a memory exhaustion crash...

GPT Academic Remote Code Execution Vulnerability

GPT Academic is an interface that provides pragmatic interactions for LLM grand language models such as GPT/GLM. GPT Academic suffers from a remote code execution vulnerability that stems from not properly validating a user-supplied RAR file, which can be exploited by an attacker to cause remote...

GPT Academic Denial of Service Vulnerability (CNVD-2025-22736)

GPT Academic is an interface that provides pragmatic interactions for LLM grand language models such as GPT/GLM. GPT Academic suffers from a denial of service vulnerability that stems from the use of insecure regular expressions. An attacker could exploit this vulnerability to cause a regular...

Malicious code in mm-react-gpt (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 9a777feae3d9f0ba145555d872c6749a18d3f877dd9617efe5a5856eb06a366e Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

Malware in mm-react-gpt

Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be rotated immediately from a different computer. The package should be removed, but as full control of the computer may have been given to an outsid...