57 citations · 103 across the 16 of their papers we have counts for
17 papers
Defending against Adaptive Prompt Injection Attacks via Reasoning-enabled Task Alignment
Lipeng He, Yihan Wang, Jiawen Zhang +1
Indirect prompt injection attacks hijack LLM-based agents by embedding malicious instructions in third-party data that the agent retrieves during task execution. Existing defenses…
SoK: Colluding Adversaries in Machine Learning Pipelines
Vasisht Duddu, Lipeng He, Asim Waheed +1
Machine learning (ML) models are susceptible to various security, privacy, and fairness risks. Adversaries with different characteristics (i.e., objectives, knowledge, and capabili…
Extracting Training Data from Diffusion Language Models via Infilling
Yihan Wang, N. Asokan
Memorization in large language models has been studied almost exclusively through prefix-conditioned extraction, a natural choice for autoregressive models. However, diffusion lang…
Locket: Robust Feature-Locking Technique for Language Models
Lipeng He, Vasisht Duddu, N. Asokan
Chatbot service providers (e.g., OpenAI) rely on tiered subscription plans to generate revenue, offering black-box access to basic models for free users and advanced models to payi…
PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing
Anthony Hughes, Vasisht Duddu, N. Asokan +2
Language models (LMs) may memorize personally identifiable information (PII) from training data, enabling adversaries to extract it during inference. Existing defense mechanisms su…
Amulet: a Python Library for Assessing Interactions Among ML Defenses and Risks
Asim Waheed, Vasisht Duddu, Sebastian Szyller
Machine learning (ML) models are susceptible to various risks to security, privacy, and fairness. Most defenses are designed to protect against each risk individually (intended int…
Combining Machine Learning Defenses without Conflicts
Vasisht Duddu, Rui Zhang, N. Asokan
Machine learning (ML) defenses protect against various risks to security, privacy, and fairness. Real-life models need simultaneous protection against multiple different risks whic…
Laminator: Verifiable ML Property Cards using Hardware-assisted Attestations
Vasisht Duddu, Oskari Järvinen, Lachlan J Gunn +1
Regulations increasingly call for various assurances from machine learning (ML) model providers about their training data, training process, and model behavior. For better transpar…
Espresso: Robust Concept Filtering in Text-to-Image Models
Anudeep Das, Vasisht Duddu, Rui Zhang +1
Diffusion based text-to-image models are trained on large datasets scraped from the Internet, potentially containing unacceptable concepts (e.g., copyright-infringing or unsafe). W…
SoK: Unintended Interactions among Machine Learning Defenses and Risks
Vasisht Duddu, Sebastian Szyller, N. Asokan
Machine learning (ML) models cannot neglect risks to security, privacy, and fairness. Several defenses have been proposed to mitigate such risks. When a defense is effective in mit…
GrOVe: Ownership Verification of Graph Neural Networks using Embeddings
Asim Waheed, Vasisht Duddu, N. Asokan
Graph neural networks (GNNs) have emerged as a state-of-the-art approach to model and draw inferences from large scale graph-structured data in various application settings such as…
On the Robustness of Dataset Inference
Sebastian Szyller, Rui Zhang, Jian Liu +1
Machine learning (ML) models are costly to train as they can require a significant amount of data, computational resources and technical expertise. Thus, they constitute valuable i…
Conflicting Interactions Among Protection Mechanisms for Machine Learning Models
Sebastian Szyller, N. Asokan
Nowadays, systems based on machine learning (ML) are widely used in different domains. Given their popularity, ML models have become targets for various attacks. As a result, resea…
SHAPr: An Efficient and Versatile Membership Privacy Risk Metric for Machine Learning
Vasisht Duddu, Sebastian Szyller, N. Asokan
Data used to train machine learning (ML) models can be sensitive. Membership inference attacks (MIAs), attempting to determine whether a particular data record was used to train an…
Extraction of Complex DNN Models: Real Threat or Boogeyman?
Buse Gul Atli, Sebastian Szyller, Mika Juuti +2
Recently, machine learning (ML) has introduced advanced solutions to many domains. Since ML models provide business advantage to model owners, protecting intellectual property of M…
DAWN: Dynamic Adversarial Watermarking of Neural Networks
Sebastian Szyller, Buse Gul Atli, Samuel Marchal +1
Training machine learning (ML) models is expensive in terms of computational power, amounts of labeled data and human expertise. Thus, ML models constitute intellectual property (I…
PRADA: Protecting against DNN Model Stealing Attacks
Mika Juuti, Sebastian Szyller, Samuel Marchal +1
Machine learning (ML) applications are increasingly prevalent. Protecting the confidentiality of ML models becomes paramount for two reasons: (a) a model can be a business advantag…