arXiv AI
Jun 16
Cordyceps: Covert Control Attacks on LLMs via Data Poisoning
arXiv:2605. 26595v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are often fine-tuned on uncurated text datasets that adversaries can poison.
Phantom Transfer: Data Poisoning can Survive Data-Level Defences
arXiv:2602. 04899v2 Announce Type: replace-cross Abstract: We present a data poisoning attack -- Phantom Transfer -- with the property that, even if you know precisely how the poison was placed into an otherwise benign dataset, you cannot filter it out.
Related stories
arXiv AI
Jul 8
Statistical Adversaries: Natural Backdoor-like Features in Vision Datasets
arXiv:2607. 05516v1 Announce Type: cross Abstract: Model-specific adversarial attacks have been extensively studied.
Hugging Face Trending Papers
Jul 7
Two Sides of the Same Coin: Learning the Backdoor to Remove the Backdoor
The community has recently developed various training-time defenses to counter neural backdoors introduced through data poisoning. In light of the observation that a model learns poisonous samples responsible for the backdoor easier than benign samples, these approaches either use a fixed threshold of the training loss for splitting or iteratively learn a reference model as an oracle for identifying benign samples.
arXiv AI
Jul 28
Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning
arXiv:2607. 23394v1 Announce Type: new Abstract: Recent work shows that fine-tuning language models on even a small amount of poisoned data can install targeted misbehavior, and ostensibly benign data can transmit hidden preferences that generalize broadly.
Hugging Face Trending Papers
Jul 6
Statistical Adversaries: Natural Backdoor-like Features in Vision Datasets
Model-specific adversarial attacks have been extensively studied. We study a different failure mode: naturally occurring statistical signals in vision data that can behave like backdoor-like triggers without being maliciously inserted.
arXiv Machine Learning
Jun 9
SoK: Reconstruction Attacks on Synthetic Tabular Data (Insights from Winning the NIST CRC)
arXiv:2606. 08372v1 Announce Type: cross Abstract: Synthetic data is increasingly promoted as a privacy-preserving substitute for releasing sensitive tabular records, yet its central adversarial threat ("reconstruction", the recovery of an individual's hidden attribute values from a synthetic release and a handful of known quasi-identifiers) has been studied only in scattered, hard-to-compare settings.
arXiv Machine Learning
Jul 8
Two Sides of the Same Coin: Learning the Backdoor to Remove the Backdoor
arXiv:2607. 05748v1 Announce Type: new Abstract: The community has recently developed various training-time defenses to counter neural backdoors introduced through data poisoning.
arXiv Machine Learning
Jun 17
Loss Landscape Poisoning: Targeted Extraction of Unseen Training Data from LLMs
arXiv:2606. 17110v1 Announce Type: cross Abstract: Large Language Models are increasingly trained on proprietary or sensitive data, from private healthcare and financial records to user conversations containing secrets.
arXiv Machine Learning
Jul 23
Membership Inference Attacks for Unseen Classes
arXiv:2506. 06488v3 Announce Type: replace Abstract: A key tool in developing safe AI models is \emph{data auditing}, i.
arXiv AI
1d ago
Statistical Adversaries: Natural Backdoor-like Adversarial Features in Clean Vision Datasets
arXiv:2607. 05516v2 Announce Type: replace-cross Abstract: Model-specific adversarial attacks have been extensively studied.
arXiv AI
Jun 9
Targeting World Models to Compromise Robot Learning Pipelines
arXiv:2606. 09499v1 Announce Type: cross Abstract: World models have recently seen a rapid growth in both their popularity and capability as more data efficient tools for generating robot training data or simulating real world environments, with many works proposing their integration into the robot learning pipeline.
arXiv AI
Jun 12
Reconstructing Template-Memorized Images from Natural Prompts
arXiv:2507. 07947v4 Announce Type: replace-cross Abstract: Recent advances in generative models, such as diffusion models, have raised concerns related to privacy, copyright infringement, and data stewardship.