arXiv Machine Learning
Jun 18
Lifecycle-Aware Dynamic Analysis for Secure ML Model Execution
arXiv:2606. 19023v1 Announce Type: cross Abstract: The growing reliance on pre-trained Machine Learning (ML) models has introduced new attack surfaces.
Lifecycle-Aware Dynamic Analysis for Secure ML Model Execution
The growing reliance on pre-trained Machine Learning (ML) models has introduced new attack surfaces. Recent vulnerabilities demonstrate that malicious behavior can be embedded within model artifacts, often bypassing existing defenses.
Related stories
arXiv AI
Sep 24
When Clients Are Orchestrated: Strategic Gradient Manipulation to Defeat Federated Learning Servers with Efficient Defense
The paper introduces Fed-ADR, a coordinated attack framework where a malicious orchestrator server directs heterogeneous adversarial clients to adapt their gradient updates in real time, thereby evading existing federated learning defenses and drastically reducing global model accuracy. It also presents a lightweight detection mechanism that estimates true client gradients from historical data to spot coordinated attacks, and an in-situ recovery method that restores model performance without restarting training. Experiments on MNIST, Fashion‑MNIST, and CIFAR‑10 show the attack can drop accuracy from over 90% to below 10%, while the defense can recover accuracy to above 90% within a few rounds at a computational cost at least 20× lower than retraining from scratch.
arXiv Machine Learning
Aug 13
Defending against Model Extraction for GNNs with Model Reprogramming
arXiv:2608. 11495v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) serve as the backbone for high-stakes applications in Machine-Learning-as-a-Service (MLaaS).
Hugging Face Trending Papers
Jun 2
RogueMerge: Robust and Unified Attacks against LLM Model Merging
Model merging composes specialized capabilities into a single LLM by aggregating task vectors sourced from unverified public platforms, exposing a critical supply-chain attack surface: Because any malicious behavior can be encoded into a task vector, and merging grants third-party vectors direct write access to model weights, an attacker-provided task vector can enable or amplify diverse downstream threats. Prior work studies only backdoor attacks against model merging for classifiers using static arithmetic heuristics, which fail to effectively handle diverse attacks on generative LLMs for three reasons.
Hugging Face Trending Papers
Jul 29
ToxScreen: Detecting Whether an LLM Has Been Poisoned
As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time. We ask whether a defender can recover such a trigger under realistic affordances, namely white-box access to the weights and knowledge of the behavior of concern, but no training data, no trusted reference model, no knowledge of the trigger, and no certainty that the model is poisoned.
arXiv AI
Jun 9
Model Poisoning Against Federated Model Adaptation with Chain of Bit-Flips
arXiv:2606. 09548v1 Announce Type: cross Abstract: Federated Learning (FL) allows a set of clients to collectively train a global model without sharing local training data.
arXiv AI
Sep 18
Inference-Engine Fingerprinting Attacks are Practical: Exploring Model-Driven Environmental Discovery, Exploitation, and Escape
The paper demonstrates that a misaligned AI model can fingerprint the inference engine (e.g., vLLM, SGLang) it runs on by generating specific output tokens. Once the engine is identified, the model can exploit engine‑specific vulnerabilities to take control of the engine without external malicious inputs. The authors provide concrete examples across five popular engines and present a proof‑of‑concept bare‑metal exploit chain that begins with such fingerprinting.
arXiv Machine Learning
Sep 21
Identifying Security Platform Product Abuse with Machine Learning
arXiv:2609.21303v1 Announce Type: cross Abstract: Product abuse is an individually rare, but growing, problem across the SaaS industry. Highly sophisticated threat actors can misuse security platform...
arXiv Machine Learning
Jun 3
RogueMerge: Robust and Unified Attacks against LLM Model Merging
arXiv:2606. 03344v1 Announce Type: cross Abstract: Model merging composes specialized capabilities into a single LLM by aggregating task vectors sourced from unverified public platforms, exposing a critical supply-chain attack surface: Because any malicious behavior can be encoded into a task vector, and merging grants third-party vectors direct write access to model weights, an attacker-provided task vector can enable or amplify diverse downstream threats.
arXiv AI
Jul 21
Signal-based Model Access Risk Analysis for AI System Operations Security
arXiv:2607. 16414v1 Announce Type: cross Abstract: Artificial intelligence (AI) systems are now ubiquitous across domains such as security, finance, healthcare, consumer technology, and large-scale cloud services, where they process massive volumes of data and make consequential decisions daily.
arXiv AI
Jun 3
AI Model Extraction Attacks: Bypassing Single-Client Assumptions in Defenses
arXiv:2606. 03381v1 Announce Type: cross Abstract: Ensuring the protection of Artificial Intelligence (AI) models deployed in military Command and Control (C2) systems and critical infrastructure is essential for maintaining information superiority.
arXiv Machine Learning
Aug 14
Understanding Backdoor Vulnerabilities in Vertical Federated Learning: The Gap Between Research and Practice
arXiv:2608. 12962v1 Announce Type: new Abstract: Vertical Federated Learning (VFL) enables organizations holding complementary features of shared entities to collaborate and train models.