AI-Enabled Influence Operation Against Iran

Citizen Lab has uncovered a coordinated AI-enabled influence operation against the Iranian government, probably conducted by Israel. Key Findings A coordinated network of more than 50 inauthentic X profiles is conducting an AI-enabled influence operation. The network, which we refer to as...

EUVD-2020-8166

Malware in sbrugna...

EUVD-2020-19811

Malware in sbrugna...

EUVD-2018-11901

Malware in sbrugna...

EUVD-2023-2456

Malicious code in bioql PyPI...

EUVD-2024-51460

Malicious code in bioql PyPI...

EUVD-2024-51462

Malicious code in bioql PyPI...

EUVD-2024-43133

Malicious code in bioql PyPI...

PT-2025-36338

Name of the Vulnerable Software and Affected Versions: Roo Code versions prior to 3.26.0 Description: Roo Code is an AI-powered autonomous coding agent. A weakness exists in the command parsing logic due to incorrect handling of Bash parameter expansion and indirect reference. If the agent was...

IMU: Influence-Guided Machine Unlearning

Recent studies have shown that deep learning models are vulnerable to attacks and tend to memorize training data points, raising significant concerns about privacy leakage. This motivates the development of machine unlearning MU, i.e., a paradigm that enables models to selectively forget specific...

PT-2025-37214

Name of the Vulnerable Software and Affected Versions: Linux kernel affected versions not specified Description: The Linux kernel contains a flaw related to file descriptor table allocations. When sysctl nr open is set to a very high value, processes attempting to use file descriptors near the...

Counterfactual Influence As a Distributional Quantity

Machine learning models are known to memorize samples from their training data, raising concerns around privacy and generalization. Counterfactual self-influence is a popular metric to study memorization, quantifying how the model's prediction for a sample changes depending on the sample's...

RepuNet: a Reputation System for Mitigating Malicious Clients in DFL

Decentralized Federated Learning DFL enables nodes to collaboratively train models without a central server, introducing new vulnerabilities since each node independently selects peers for model aggregation. Malicious nodes may exploit this autonomy by sending corrupted models model poisoning,...

Unlearning-Enhanced Website Fingerprinting Attack: against Backdoor Poisoning in Anonymous Networks

Website Fingerprinting WF is an effective tool for regulating and governing the dark web. However, its performance can be significantly degraded by backdoor poisoning attacks in practical deployments. This paper aims to address the problem of hidden backdoor poisoning attacks faced by Website...

IF-GUIDE: Influence Function-Guided Detoxification of LLMs

We study how training data contributes to the emergence of toxic behaviors in large-language models. Most prior work on reducing model toxicity adopts $reactive$ approaches, such as fine-tuning pre-trained and potentially toxic models to align them with human values. In contrast, we propose a...

Report on the Malicious Uses of AI

OpenAI just published its annual report on malicious uses of AI. By using AI as a force multiplier for our expert investigative teams, in the three months since our last report we’ve been able to detect, disrupt and expose abusive activity including social engineering, cyber espionage, deceptive...

Meta Disrupts Influence Ops Targeting Romania, Azerbaijan, and Taiwan with Fake Personas

Meta on Thursday revealed that it disrupted three covert influence operations originating from Iran, China, and Romania during the first quarter of 2025. "We detected and removed these campaigns before they were able to build authentic audiences on our apps," the social media giant said in its...

Meta Disrupts Influence Ops Targeting Romania, Azerbaijan, and Taiwan with Fake Personas

Meta on Thursday revealed that it disrupted three covert influence operations originating from Iran, China, and Romania during the first quarter of 2025. "We detected and removed these campaigns before they were able to build authentic audiences on our apps," the social media giant said in its...

CVE-2021-45908

An issue was discovered in gif2apng 1.9. There is a stack-based buffer overflow involving a while loop. An attacker has little influence over the data written to the stack, making it unlikely that the flow of control can be subverted...

ChestyBot: Detecting and Disrupting Chinese Communist Party Influence Stratagems

Foreign information operations conducted by Russian and Chinese actors exploit the United States' permissive information environment. These campaigns threaten democratic institutions and the broader Westphalian model. Yet, existing detection and mitigation strategies often fail to identify active...