REVIEW 18 cited by
Privacy in Large Language Models: Attacks, Defenses and Future Directions
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
The advancement of large language models (LLMs) has significantly enhanced the ability to effectively tackle various downstream NLP tasks and unify these tasks into generative pipelines. On the one hand, powerful language models, trained on massive textual data, have brought unparalleled accessibility and usability for both models and users. On the other hand, unrestricted access to these models can also introduce potential malicious and unintentional privacy risks. Despite ongoing efforts to address the safety and privacy concerns associated with LLMs, the problem remains unresolved. In this paper, we provide a comprehensive analysis of the current privacy attacks targeting LLMs and categorize them according to the adversary's assumed capabilities to shed light on the potential vulnerabilities present in LLMs. Then, we present a detailed overview of prominent defense strategies that have been developed to counter these privacy attacks. Beyond existing works, we identify upcoming privacy concerns as LLMs evolve. Lastly, we point out several potential avenues for future exploration.
Forward citations
Cited by 18 Pith papers
-
MultivationBench: A Benchmark for Multimodal Sequential Motivation Reasoning
MultivationBench, a 16,092-question picture-story benchmark grounded in Maslow's and Reiss's motivation theories, shows that all tested multimodal LLMs score well below humans and almost never maintain consistent moti...
-
SkipOPU: An FPGA-based Overlay Processor for Large Language Models with Dynamically Allocated Computation
An FPGA accelerator for SkipGPT-style pruned LLMs that fuses router/normalization/attention computation to hide nonlinear latency, packs two FP16 products in each DSP, and serves reused KV entries from on-chip URAM to...
-
The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer
Text jailbreak prompts converted to audio match or beat dedicated audio jailbreaks on omni-models, and transfer success tracks how tightly the model aligns text and audio representations.
-
LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems
A systematic review that categorizes LLM threats, severity scores, and mitigations across development and operation life cycles and multiple deployment scenarios.
-
Towards Provable (In)Secure Model Weight Release Schemes
Defines game-based security for weight release schemes and breaks TaylorMLP with a near-complete, low-cost parameter extraction attack.
-
XToM: Exploring the Multilingual Theory of Mind for Large Language Models
XToM translates three English theory-of-mind benchmarks into Chinese, German, French, and Japanese with human quality control, and shows LLMs' belief reasoning is weaker and less consistent across languages than their...
-
Understanding and Mitigating Cross-lingual Privacy Leakage via Language-specific and Universal Privacy Neurons
Cross-lingual privacy leakage in LLMs is driven by a mix of language-universal and language-specific neurons, and deactivating those neurons lowers measured leakage by 23.3% to 31.6%.
-
HealthSLM-Bench: Benchmarking Small Language Models for Mobile and Wearable Healthcare Monitoring
Small language models rival large ones on several wearable health prediction tasks, with large efficiency gains, but suffer from class imbalance and poor calorie regression.
-
Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning
A Context Reasoner pipeline that cold-starts LLMs on distilled legal reasoning and applies PPO with a rule-based compliance reward improves performance on CI-based legal compliance benchmarks and transfers to general ...
-
AIDBench: A benchmark for evaluating the authorship identification capability of large language models
A new benchmark shows GPT-4 and several other LLMs can attribute anonymous texts to their authors at rates well above random chance, though performance drops sharply in harder cross-topic settings.
-
Public Data Assisted Differentially Private In-Context Learning
A private ICL algorithm that aggregates LLM responses with DPM clustering and uses public data representatives achieves near-non-private utility at epsilon=1.
-
Information Leakage of Sentence Embeddings via Generative Embedding Inversion Attacks
GEIA embedding-inversion results are reproducible across five sentence embedders, and a log-likelihood comparison of masked versus alternative sentences indicates sentence embeddings can expose masked named entities, ...
-
Deep Learning Model Inversion Attacks and Defenses: A Comprehensive Survey
A structured literature review that taxonomizes model inversion attacks and defenses and provides a public resource repository.
-
Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier
Aya Expanse 8B and 32B report state-of-the-art multilingual win-rates on a new 23-language translated Arena-Hard benchmark, with the 32B beating Llama 3.1 70B by 54.0%.
-
LLM Security: Vulnerabilities, Attacks, Defenses, and Countermeasures
This survey categorizes attacks on large language models by lifecycle phase and maps them to prevention and detection defenses, concluding that only a few defenses are highly effective.
-
Privacy in Fine-tuning Large Language Models: Attacks, Defenses, and Future Directions
A structured survey of attacks and defenses for privacy during LLM fine-tuning, grouped by fine-tuning method and pre-trained model.
-
Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities
A tutorial reviewing LLM alignment through the lens of inverse reinforcement learning, arguing that neural reward models learned from human data are central to post-training.
-
Attack and defense techniques in large language models: A survey and new perspectives
A survey taxonomizing LLM attacks into prompt, optimized, application-level, and model-theft categories, and defenses into prevention and detection categories, with no new empirical results.
Discussion (0). Continue with ORCID to comment.