aisecwatch.com
DashboardVulnerabilitiesNewsResearchArchiveStatsDatasetFor devs
Subscribe
aisecwatch.com

Real-time AI security monitoring. Tracking AI-related vulnerabilities, safety and security incidents, privacy risks, research developments, and policy changes.

Navigation

VulnerabilitiesNewsResearchDigest ArchiveNewsletter ArchiveSubscribeData SourcesStatisticsDatasetAPIIntegrationsWidgetRSS Feed

Maintained by

Truong (Jack) Luu

Information Systems Researcher

Research

Academic papers, new techniques, benchmarks, and theoretical findings in AI/LLM security.

to
Export CSV
336 items

Privacy Against Agnostic Inference Attacks in Vertical Federated Learning

inforesearchPeer-Reviewed
securityprivacy
May 7, 2026

This academic paper examines privacy risks in vertical federated learning (a machine learning approach where different organizations each hold different features of the same data and train a model together) when facing agnostic inference attacks (attacks where the attacker doesn't know the model's structure in advance). The paper analyzes how attackers could potentially infer private information from the shared computations in this system.

ACM Digital Library (TOPS, DTRAP, CSUR)

v5.6.1

inforesearchIndustry
security

Privacy-preserving path constrained shortest distance queries on encrypted graphs

inforesearchPeer-Reviewed
security

CTISum: A new benchmark dataset for Cyber Threat Intelligence summarization

inforesearchPeer-Reviewed
research

v5.6.0

inforesearchIndustry
industry

K-TCDP: A Temporal Correlated DP Mechanism for LoRA Supervised Fine-Tuning

inforesearchPeer-Reviewed
research

FinBot CTF Is Live: A Hands-On Companion to the OWASP GenAI Security Project

inforesearchIndustry
security

Privacy-preserving for user-uploaded images and text in Vision-Language Models

inforesearchPeer-Reviewed
privacy

A Survey of Algorithm Debt in Machine and Deep Learning Systems: Definition, Smells, and Future Work

inforesearchPeer-Reviewed
research

SBOMs into Agentic AIBOMs: Schema Extensions, Agentic Orchestration and Reproducibility Evaluation

inforesearchPeer-Reviewed
research

Benchmarking the effectiveness of multi-agent LLMs in collaborative privacy threat modeling with <span class="small-caps">LINDDUN GO</span>

inforesearchPeer-Reviewed
research

Enabling trust and learner agency in lifelong learning: A dual-chain, privacy-preserving credential architecture

inforesearchPeer-Reviewed
security

R-FLoRA: Residual-Statistic-Gated Low-Rank Adaptation for Single-Image Face Morphing Attack Detection

inforesearchPeer-Reviewed
research

FDXT: Forward and Backward Private Conjunctive Searchable Encryption to Suppress Volume Leakages Caused by Cross-Tags

inforesearchPeer-Reviewed
security

Fingerprint-based watermarking for protecting and tracing black-box NLP models

inforesearchPeer-Reviewed
security

AI-Enhanced Cybersecurity in Edge Computing: Threats, Solutions, and Future Directions

inforesearchPeer-Reviewed
security

Anubis : A smart context-aware security model for access control

inforesearchPeer-Reviewed
security

Optimizing stealthiness in universal adversarial perturbations via class-selective and perceptual similarity metrics

inforesearchPeer-Reviewed
security

ThreatMAMBA: Achieving High-Robustness Cyber Threat Attribution During the Evolution of Attacks

inforesearchPeer-Reviewed
research

LLLMs: A Data-Driven Survey of Evolving Research on Limitations of Large Language Models

inforesearchPeer-Reviewed
research
1 / 17Next
May 5, 2026

N/A -- This content is a navigation menu and product listing from GitHub's website (v5.6.1), not a security issue, vulnerability report, or technical problem. It describes GitHub's features like Copilot (an AI coding assistant), Actions (workflow automation), and security tools, but contains no substantive technical content to analyze.

MITRE ATLAS Releases
May 3, 2026

This research paper, published in September 2026, addresses how to find the shortest path between two points on encrypted graphs (networks where connections and data are hidden using cryptography) while keeping the query private. The work focuses on path-constrained queries, meaning the shortest route must follow specific rules or limitations, all without revealing the actual graph structure or what users are searching for.

Elsevier Security Journals
May 2, 2026

CTISum is a new benchmark dataset designed to help train and test AI systems that automatically summarize cyber threat intelligence (CTI, which is information about security attacks and threats). The dataset provides examples of threat reports and their summaries, helping researchers develop better AI tools for quickly understanding large amounts of security information. This work addresses the challenge of processing the massive volume of threat data that security teams need to analyze.

Elsevier Security Journals
Apr 30, 2026

N/A -- The provided content is a navigation menu and feature listing from GitHub's website, not an AI/LLM security issue, vulnerability, or technical problem.

MITRE ATLAS Releases
privacy
Apr 29, 2026

This research proposes K-TCDP (K-Temporal Correlated Differential Privacy), a new method for training large language models privately using LoRA (a technique that adds small trainable adapters to a model). Standard privacy-preserving training adds random noise that degrades model quality, but K-TCDP uses strategically correlated noise over time so that noise added in early steps can be partially canceled out by noise in later steps, improving model performance while maintaining privacy guarantees.

IEEE Xplore (Security & AI Journals)
research
Apr 28, 2026

FinBot is an interactive training platform (CTF, or capture-the-flag competition) created by OWASP to help builders and defenders understand how agentic AI systems (AI agents that plan, act, and make decisions in complex workflows) can fail and be attacked. It simulates a financial services application where users encounter real security risks like prompt injection (tricking an AI by hiding instructions in its input), tool misuse, data theft, and privilege escalation (gaining unauthorized higher-level access), with connections to industry security frameworks like the OWASP Top 10 for Agentic Applications.

OWASP GenAI Security
research
Apr 28, 2026

Vision-language models (AI systems that process both images and text together) can leak private information from user-uploaded content, such as identifying people in photos or extracting sensitive text. This research examines privacy risks when users submit images and text to these models. The paper proposes privacy-preserving methods to protect user data while still allowing these AI systems to function effectively.

Elsevier Security Journals
Apr 28, 2026

This survey paper examines algorithm debt in machine learning and deep learning systems, which refers to the long-term costs and problems that accumulate when developers use suboptimal algorithms or methods in AI projects. The paper defines what algorithm debt is, identifies warning signs called 'smells' that indicate its presence, and discusses future research directions. Understanding algorithm debt helps developers recognize when quick, temporary solutions in AI projects create technical problems that become harder and more expensive to fix later.

ACM Digital Library (TOPS, DTRAP, CSUR)
Apr 27, 2026

This academic paper explores how Software Bill of Materials (SBOMs, detailed lists of all software components used in a project) can be extended to cover agentic AI systems (AI systems that can independently make decisions and take actions). The paper discusses schema extensions, how to organize and orchestrate these agentic components, and methods to evaluate whether AI systems produce reproducible results.

ACM Digital Library (TOPS, DTRAP, CSUR)
security
Apr 26, 2026

This research paper evaluates whether multiple AI agents working together can effectively help identify privacy threats in software systems using LINDDUN GO, a structured methodology for privacy threat modeling (a process of identifying ways a system could leak or misuse personal data). The study, published in July 2026, examines whether collaborative multi-agent LLM (large language model) systems can improve the quality and completeness of privacy threat identification compared to single AI agents or human analysis.

Elsevier Security Journals
privacy
Apr 23, 2026

This academic paper proposes a dual-chain, privacy-preserving credential architecture designed to enable trust and learner agency in lifelong learning systems. The work focuses on creating secure credential management that protects learner privacy while maintaining verifiable educational records across multiple institutions and learning contexts.

Elsevier Security Journals
security
Apr 23, 2026

Face morphing attacks (blending two faces together to fool facial recognition systems) threaten security systems used at borders and for digital identity checks, and detecting them from a single image is difficult because there's no trusted reference image to compare against. This paper presents R-FLoRA, a new detection method that combines high-frequency image analysis (looking at fine details) with a frozen, large-scale vision transformer (a type of AI model trained on images) to spot morphing artifacts while keeping the overall understanding of the face intact. The method outperforms nine other detection approaches on multiple test datasets and works efficiently in real-world biometric verification systems.

IEEE Xplore (Security & AI Journals)
Apr 23, 2026

This paper describes a new encryption method called FDXT that helps protect data privacy when searching encrypted files on untrusted servers. Previous methods like ODXT and SDSSE-CQ had weaknesses where attackers could leak information by analyzing search patterns and file sizes when users searched for multiple keywords together, but FDXT fixes these privacy leaks while maintaining similar or better performance.

IEEE Xplore (Security & AI Journals)
research
Apr 22, 2026

Researchers have developed a fingerprint-based watermarking technique to protect and track natural language processing models (AI systems trained to understand and generate text) that operate as black boxes (systems where users cannot see how internal decisions are made). This method allows owners to prove they created a model and trace where it has been used or copied without permission.

Elsevier Security Journals
research
Apr 22, 2026

This academic survey article examines how AI is being used to improve security in edge computing (processing data on devices near users rather than in distant data centers), while also exploring the new threats that arise when combining AI with edge systems. The article covers both the security challenges unique to AI-enhanced edge environments and potential approaches to address them, looking toward future developments in this field.

ACM Digital Library (TOPS, DTRAP, CSUR)
Apr 20, 2026

Anubis is a security model designed to control access to systems by understanding the context in which access requests are made, rather than using fixed rules alone. The model aims to make access control smarter by considering situational factors when deciding whether to grant or deny user permissions. This research was published in July 2026 in the Journal of Information Security and Applications.

Elsevier Security Journals
research
Apr 20, 2026

Universal Adversarial Perturbations (UAPs, tiny modifications to images that fool AI models across many different inputs) are security threats to deep learning systems, but existing methods make attacks obvious because they either look wrong to humans or cause suspicious misclassifications. This paper presents Stealthy-UAP, a framework that makes UAPs harder to detect by targeting only semantically related classes (so misclassifications seem plausible) and optimizing perturbations to match how humans actually perceive images.

Elsevier Security Journals
security
Apr 20, 2026

Cyber Threat Attribution (CTA) is the process of identifying who carried out a cyberattack by analyzing evidence from the attack. This paper introduces ThreatMAMBA, an AI framework that improves CTA by building knowledge graphs from threat intelligence data (IOCs, or indicators of compromise that identify malicious activity; TTPs, or tactics and techniques used by attackers; and temporal relationships) and using machine learning to identify attackers even in the early stages of ongoing attacks. The system showed significant improvements in accuracy at different stages of attack development, suggesting it can provide reliable attribution information quickly during real incidents.

IEEE Xplore (Security & AI Journals)
Apr 18, 2026

This is a research survey published in ACM Computing Surveys that examines the limitations and problems of large language models (LLMs, which are AI systems trained on massive amounts of text data to generate human-like responses). The survey takes a data-driven approach to understand how LLM research has evolved as scientists discover and study these systems' weaknesses and constraints.

ACM Digital Library (TOPS, DTRAP, CSUR)