13735 matches found
CVE-2025-54412
skops is a Python library which helps users share and ship their scikit-learn based models. Versions 0.11.0 and below contain a inconsistency in the OperatorFuncNode which can be exploited to hide the execution of untrusted operator methods. This can then be used in a code reuse attack to invoke...
CVE-2025-54412 skops' Inconsistent Trusted Type Validation Enables Hidden `operator` Methods Execution
skops is a Python library which helps users share and ship their scikit-learn based models. Versions 0.11.0 and below contain a inconsistency in the OperatorFuncNode which can be exploited to hide the execution of untrusted operator methods. This can then be used in a code reuse attack to invoke...
ModShift: Model Privacy Via Designed Shifts
In this paper, shifts are introduced to preserve model privacy against an eavesdropper in federated learning. Model learning is treated as a parameter estimation problem. This perspective allows us to derive the Fisher Information matrix of the model updates from the shifted updates and drive the...
Trivial Trojans: How Minimal MCP Servers Enable Cross-Tool Exfiltration of Sensitive Data
The Model Context Protocol MCP represents a significant advancement in AI-tool integration, enabling seamless communication between AI agents and external services. However, this connectivity introduces novel attack vectors that remain largely unexplored. This paper demonstrates how unsophisticat...
Information Exposure
Overview Affected versions of this package are vulnerable to Information Exposure via the q URL parameter in the /api/v2.0/users endpoint. An attacker can retrieve sensitive password hash and salt values by abusing the filtering capability to extract this information character by character. Note:...
Subliminal Learning in AIs
Today's freaky LLM behavior: We study subliminal learning, a surprising phenomenon where language models learn traits from model-generated data that is semantically unrelated to those traits. For example, a "student" model learns to prefer owls when trained on sequences of numbers generated by a...
PurpCode: Reasoning for Safer Code Generation
We introduce PurpCode, the first post-training recipe for training safe code reasoning models towards generating secure code and defending against malicious cyberactivities. PurpCode trains a reasoning model in two stages: i Rule Learning, which explicitly teaches the model to reference cybersafe...
Generating Adversarial Point Clouds Using Diffusion Model
Adversarial attack methods for 3D point cloud classification reveal the vulnerabilities of point cloud recognition models. This vulnerability could lead to safety risks in critical applications that use deep learning models, such as autonomous vehicles. To uncover the deficiencies of these models...
OneShield -- the Next Generation of LLM Guardrails
The rise of Large Language Models has created a general excitement about the great potential for a myriad of applications. While LLMs offer many possibilities, questions about safety, privacy, and ethics have emerged, and all the key actors are working to address these issues with protective...
Tenda FH451 formSafeUrlFilter Function Buffer Overflow Vulnerability
The Tenda FH451 is a router from the Chinese company Tenda. The Tenda FH451 version 1.0.0.9 suffers from a buffer overflow vulnerability that originates from a failure to properly validate the length of input data for the parameter Go/page in the file /goform/SafeUrlFilter, which could be exploit...
Auto-SGCR: Automated Generation of Smart Grid Cyber Range Using IEC 61850 Standard Models
Digitalization of power grids have made them increasingly susceptible to cyber-attacks in the past decade. Iterative cybersecurity testing is indispensable to counter emerging attack vectors and to ensure dependability of critical infrastructure. Furthermore, these can be used to evaluate...
Information Security Based on LLM Approaches: a Review
Information security is facing increasingly severe challenges, and traditional protection means are difficult to cope with complex and changing threats. In recent years, as an emerging intelligent technology, large language models LLMs have shown a broad application prospect in the field of...
Regression-Aware Continual Learning for Android Malware Detection
Malware evolves rapidly, forcing machine learning ML-based detectors to adapt continuously. With antivirus vendors processing hundreds of thousands of new samples daily, datasets can grow to billions of examples, making full retraining impractical. Continual learning CL has emerged as a scalable...
LoRA-Leak: Membership Inference Attacks against LoRA Fine-Tuned Language Models
Language Models LMs typically adhere to a "pre-training and fine-tuning" paradigm, where a universal pre-trained model can be fine-tuned to cater to various specialized domains. Low-Rank Adaptation LoRA has gained the most widespread use in LM fine-tuning due to its lightweight computational cost...
Quantifying the ROI of Cyber Threat Intelligence: a Data-Driven Approach
The valuation of Cyber Threat Intelligence CTI remains a persistent challenge due to the problem of negative evidence: successful threat prevention results in non-events that generate minimal observable financial impact, making CTI expenditures difficult to justify within traditional cost-benefit...
Tab-MIA: a Benchmark Dataset for Membership Inference Attacks on Tabular Data in LLMs
Large language models LLMs are increasingly trained on tabular data, which, unlike unstructured text, often contains personally identifiable information PII in a highly structured and explicit format. As a result, privacy risks arise, since sensitive records can be inadvertently retained by the...
On One-Shot Signatures, Quantum Vs Classical Binding, and Obfuscating Permutations
One-shot signatures OSS were defined by Amos, Georgiou, Kiayias, and Zhandry STOC'20. These allow for signing exactly one message, after which the signing key self-destructs, preventing a second message from ever being signed. While such an object is impossible classically, Amos et al observe tha...
Trusted Data Fusion, Multi-Agent Autonomy, Autonomous Vehicles
Multi-agent collaboration enhances situational awareness in intelligence, surveillance, and reconnaissance ISR missions. Ad hoc networks of unmanned aerial vehicles UAVs allow for real-time data sharing, but they face security challenges due to their decentralized nature, making them vulnerable t...
CVE-2025-46686
Redis through 8.0.3 allows memory consumption via a multi-bulk command composed of many bulks, sent by an authenticated user. This occurs because the server allocates memory for the command arguments of every bulk, even when the command is skipped because of insufficient permissions. NOTE: this i...
