Towards Provably Secure Generative AI: Reliable Consensus Sampling (2026.findings-acl)
Copied to clipboard
Yu Cui, Hang Fu, Sicheng Pan, Zhuoyu Sun, Yifei Liu, Yuhong Nie, Bo Ran, Baohan Huang, Xufeng Zhang, Haibin Zhang, Cong Zuo, Licheng Wang
| Challenge: | Existing research on generative AI security is driven by mutually reinforcing attack and defense methodologies grounded in empirical experience. |
| Approach: | They propose a new algorithm that uses a random sampling algorithm to control risk. |
| Outcome: | The proposed algorithm improves robustness and utility while maintaining latency comparable to existing algorithms. |
Similar Papers
Guardrails and Security for LLMs: Safe, Secure and Controllable Steering of LLM Applications (2025.acl-tutorials)
Copied to clipboard
Traian Rebedea, Leon Derczynski, Shaona Ghosh, Makesh Narsimhan Sreedhar, Faeze Brahman, Liwei Jiang, Bo Li, Yulia Tsvetkov, Christopher Parisien, Yejin Choi
| Challenge: | Pretrained generative models provide novel ways for users to interact with computers. |
| Approach: | This tutorial provides an overview of key guardrail mechanisms developed for LLMs along with evaluation methodologies and a detailed security assessment protocol. |
| Outcome: | This tutorial provides an overview of key guardrail mechanisms developed for LLMs, along with evaluation methodologies and a detailed security assessment protocol. |
Speculative Decoding for Multi-Sample Inference (2025.findings-emnlp)
Copied to clipboard
Yiwei Li, Jiayi Shi, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Yueqi Zhang, Ji Zhang, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li
| Challenge: | Speculative decoding method exploits consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or external databases. |
| Approach: | They propose a speculative decoding method that exploits the consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or external databases. |
| Outcome: | The proposed method exploits the intrinsic consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or databases. |
DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) can replicate insecure patterns from training data. |
| Approach: | They propose a framework that leverages distributed security-relevant cues by aggregating representations from multiple upper layers via an attention-based module. |
| Outcome: | Experiments show that the framework improves the secure-and-correct generation rate by 11.9% over baselines. |
Survival of the Safest: Towards Secure Prompt Optimization through Interleaved Multi-Objective Evolution (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Experimental evaluations across diverse benchmark datasets affirm ‘s efficacy in delivering high performance and notably enhancing safety and security compared to single-objective methods. |
| Approach: | They propose a multi-objective prompt optimization framework that integrates semantic, feedback, and crossover mutations to effectively traverse the prompt landscape. |
| Outcome: | The proposed framework enhances both performance and security in large language models while keeping computational demands low. |
On Guardrail Models’ Robustness to Mutations and Adversarial Attacks (2025.findings-emnlp)
Copied to clipboard
| Challenge: | generative AI systems providing unsafe information has raised significant concerns, emphasizing the need for safety guardrails. |
| Approach: | They propose to evaluate 15 state-of-the-art guardrail models to assess their robustness to input mutations and adversarial attacks designed to bypass models’ safety alignment. |
| Outcome: | The proposed models are robust to input mutations and adversarial attacks that bypass models’ safety alignment. |
Evaluating Robustness of Generative Search Engine on Adversarial Factoid Questions (2024.findings-acl)
Copied to clipboard
Xuming Hu, Xiaochuan Li, Junzhe Chen, Yinghui Li, Yangning Li, Xiaoguang Li, Yasheng Wang, Qun Liu, Lijie Wen, Philip Yu, Zhijiang Guo
| Challenge: | Existing large language models (LLMs)-backed generative search engines may not always be accurate. |
| Approach: | They propose to evaluate the robustness of retrieval-augmented generation in a realistic and high-risk setting where adversaries have only black-box system access. |
| Outcome: | The proposed model exhibits higher susceptibility to factual errors compared to LLMs without retrieval. |
Breaking the "Provable Security": Detecting Finite-Precision Artifacts in LLM-based Steganography via Low-Probability Vanishing (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models have fostered a new class of generative linguistic steganography, claim “provably secure” by theoretically aligning the stego distribution with the language model’s natural distribution. |
| Approach: | They propose a framework that transforms the detection task from semantic classification to a statistical audit of the sampling mechanism. |
| Outcome: | The proposed framework breaks the security of AC and Meteor with high detection accuracy, whereas state-of-the-art semantic steganalyzers degrade to random guessing. |
Breaking Consensus Bias: Unsupervised Reinforcement Learning for Machine Translation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing RL approaches for MT face fixed references or the production of homogeneous references leading to mode collapse in unsupervised settings. |
| Approach: | They propose an Entropy-Driven Unsupervised RL framework for machine translation that leverages entropy for supervision construction and self-evolution. |
| Outcome: | The proposed framework outperforms supervised and unsupervised baselines in multiple language pairs. |
SAFE: A Sparse Autoencoder-Based Framework for Robust Query Enrichment and Hallucination Mitigation in LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models suffer from hallucinations, which can undermine their performance in critical applications. |
| Approach: | They propose a framework for detecting and mitigating hallucinations by leveraging SAEs. |
| Outcome: | The proposed framework improves query generation accuracy and mitigates hallucinations across datasets. |
Measure and Improve Robustness in NLP Models: A Survey (2022.naacl-main)
Copied to clipboard
| Challenge: | Despite the performance gains, NLP models are still fragile and brittle to out-of-domain data, adversarial attacks, or small perturbation to the input. |
| Approach: | They propose a survey of how to define, measure and improve robustness in NLP by connecting multiple definitions of robustness and identifying failures. |
| Outcome: | The proposed models are robust against unseen or challenging scenarios, but are still fragile and brittle to out-of-domain data and adversarial attacks. |