REVIEW 12 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
Privacy in Large Language Models: Attacks, Defenses and Future Directions
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 12 Pith papers
-
Probing Memorization of Tabular In-Context Learning
A new probing framework detects moderate parametric memorization signals in tabular in-context learning models under single-task fine-tuning, strongest on low-cardinality tasks, but signals largely disappear under rea...
-
Understanding User Privacy Perceptions of GenAI Smartphones
Users show limited grasp of GenAI smartphone data practices but heightened privacy concerns across collection, storage, and control, calling for better transparency and user controls.
-
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...
-
COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling
COMPASS uses semantic clustering on multilingual embeddings to select auxiliary data for PEFT adapters, outperforming linguistic-similarity baselines on multilingual benchmarks while supporting continual adaptation.
-
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.
-
RedDiffuser: Auditing Multimodal Safety Failures in Vision-Language Models via Reinforced Diffusion
RedDiffuser is a reinforced diffusion framework that generates adversarial visual contexts to audit and expose widespread multimodal safety failures in VLMs, increasing unsafe response rates by up to 10.69% on LLaVA w...
-
Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework
Safe-SAIL supplies a pre-explanation metric and segment-level simulation to interpret 1758 safety SAE features across pornography, politics, violence, and terror, with public models and tools released.
-
AI Healthcare Chatbots as Information Infrastructure: A Large-Scale Study of User-Reported Breakdowns
Topic modeling of 15,000+ reviews from 59 AI healthcare chatbot apps reveals three main user-reported breakdowns and associates privacy issues with the most negative experiences.
-
On the Privacy of LLMs: An Ablation Study
Privacy attacks on LLMs show strong signals for membership inference and backdoors but weaker performance for attribute inference and data extraction, with risks highly dependent on system configuration.
-
LLM-CEG: Extending the Classification Error Gauge Framework for Privacy Auditing of Large Language Models
LLM-CEG applies differential privacy during fine-tuning of DistilGPT-2 to reduce membership inference attack success by 71.5% while increasing out-of-distribution utility by 47-50%.
-
Sentra-Guard: A Real-Time Multilingual Defense Against Adversarial LLM Prompts
Sentra-Guard reports 99.96% detection of adversarial LLM prompts with AUC 1.00 and ASR of 0.004% using a hybrid SBERT-FAISS and transformer classifier architecture with multilingual translation and human feedback.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.