Split Happens: Combating Advanced Threats with Split Learning and Function Secret Sharing

Split Learning SL -- splits a model into two distinct parts to help protect client data while enhancing Machine Learning ML processes. Though promising, SL has proven vulnerable to different attacks, thus raising concerns about how effective it may be in terms of data privacy. Recent works have...

When and Where Do Data Poisons Attack Textual Inversion?

Poisoning attacks pose significant challenges to the robustness of diffusion models DMs. In this paper, we systematically analyze when and where poisoning attacks textual inversion TI, a widely used personalization technique for DMs. We first introduce Semantic Sensitivity Maps, a novel method fo...

Model Inversion Attacks on Llama 3: Extracting PII from Large Language Models

Large language models LLMs have transformed natural language processing, but their ability to memorize training data poses significant privacy risks. This paper investigates model inversion attacks on the Llama 3.2 model, a multilingual LLM developed by Meta. By querying the model with carefully...

Diffusion-Based Task-Oriented Semantic Communications with Model Inversion Attack

Semantic communication has emerged as a promising neural network-based system design for 6G networks. Task-oriented semantic communication is a novel paradigm whose core goal is to efficiently complete specific tasks by transmitting semantic information, optimizing communication efficiency and ta...

InverTune: Removing Backdoors from Multimodal Contrastive Learning Models Via Trigger Inversion and Activation Tuning

Multimodal contrastive learning models like CLIP have demonstrated remarkable vision-language alignment capabilities, yet their vulnerability to backdoor attacks poses critical security risks. Attackers can implant latent triggers that persist through downstream tasks, enabling malicious control ...

AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models

We introduce AIRTBench, an AI red teaming benchmark for evaluating language models' ability to autonomously discover and exploit Artificial Intelligence and Machine Learning AI/ML security vulnerabilities. The benchmark consists of 70 realistic black-box capture-the-flag CTF challenges from the...

Byzantine Outside, Curious Inside: Reconstructing Data through Malicious Updates

Federated learning FL enables decentralized machine learning without sharing raw data, allowing multiple clients to collaboratively learn a global model. However, studies reveal that privacy leakage is possible under commonly adopted FL protocols. In particular, a server with access to client...

DiffUMI: Training-Free Universal Model Inversion Via Unconditional Diffusion for Face Recognition

Face recognition technology presents serious privacy risks due to its reliance on sensitive and immutable biometric data. To address these concerns, such systems typically convert raw facial images into embeddings, which are traditionally viewed as privacy-preserving. However, model inversion...

Symbolic Generation and Modular Embedding of High-Quality Abc-Triples

We present a symbolic identity for generating integer triples $a, b, c$ satisfying $a + b = c$, inspired by structural features of the \emphabc conjecture. The construction uses powers of $2$ and $3$ in combination with modular inversion in $\mathbbZ/3^p\mathbbZ$, leading to a parametric identity...

TimeWak: Temporal Chained-Hashing Watermark for Time Series Data

Synthetic time series generated by diffusion models enable sharing privacy-sensitive datasets, such as patients' functional MRI records. Key criteria for synthetic data include high data utility and traceability to verify the data source. Recent watermarking methods embed in homogeneous latent...

Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning

Federated learning FL allows multiple data-owners to collaboratively train machine learning models by exchanging local gradients, while keeping their private data on-device. To simultaneously enhance privacy and training efficiency, recently parameter-efficient fine-tuning PEFT of large-scale...

Unlearning Inversion Attacks for Graph Neural Networks

Graph unlearning methods aim to efficiently remove the impact of sensitive data from trained GNNs without full retraining, assuming that deleted information cannot be recovered. In this work, we challenge this assumption by introducing the graph unlearning inversion attack: given only black-box...

Shadow Defense against Gradient Inversion Attack in Federated Learning

Federated learning FL has emerged as a transformative framework for privacy-preserving distributed training, allowing clients to collaboratively train a global model without sharing their local data. This is especially crucial in sensitive fields like healthcare, where protecting patient data is...

On the Intractability of Chaotic Symbolic Walks: toward a Non-Algebraic Post-Quantum Hardness Assumption

Most classical and post-quantum cryptographic assumptions, including integer factorization, discrete logarithms, and Learning with Errors LWE, rely on algebraic structures such as rings or vector spaces. While mathematically powerful, these structures can be exploited by quantum algorithms or...

LAGO: Few-Shot Crosslingual Embedding Inversion Attacks Via Language Similarity-Aware Graph Optimization

We propose LAGO - Language Similarity-Aware Graph Optimization - a novel approach for few-shot cross-lingual embedding inversion attacks, addressing critical privacy vulnerabilities in multilingual NLP systems. Unlike prior work in embedding inversion attacks that treat languages independently,...

BeamClean: Language Aware Embedding Reconstruction

In this work, we consider an inversion attack on the obfuscated input embeddings sent to a language model on a server, where the adversary has no access to the language model or the obfuscation mechanism and sees only the obfuscated embeddings along with the model's embedding table. We propose...

Verifiably Forgotten? Gradient Differences Still Enable Data Reconstruction in Federated Unlearning

Federated Unlearning FU has emerged as a critical compliance mechanism for data privacy regulations, requiring unlearned clients to provide verifiable Proof of Federated Unlearning PoFU to auditors upon data removal requests. However, we uncover a significant privacy vulnerability: when gradient...

A Numerical Gradient Inversion Attack in Variational Quantum Neural-Networks

The loss landscape of Variational Quantum Neural Networks VQNNs is characterized by local minima that grow exponentially with increasing qubits. Because of this, it is more challenging to recover information from model gradients during training compared to classical Neural Networks NNs. In this...

A Survey on Privacy Risks and Protection in Large Language Models

Although Large Language Models LLMs have become increasingly integral to diverse applications, their capabilities raise significant privacy concerns. This survey offers a comprehensive overview of privacy risks associated with LLMs and examines current solutions to mitigate these challenges. Firs...

An Inversion Theorem for Buffered Linear Toeplitz (BLT) Matrices and Applications to Streaming Differential Privacy

Buffered Linear Toeplitz BLT matrices are a family of parameterized lower-triangular matrices that play an important role in streaming differential privacy with correlated noise. Our main result is a BLT inversion theorem: the inverse of a BLT matrix is itself a BLT matrix with different...