Zhensu Sun — accepted AI-conference papers

2026

Autoregressive, Yet Revisable: In Decoding Revision for Secure Code Generation

Chengran Yang, zichao wei, Heminghao Deng, Jinfeng Jiang, Zhensu Sun, Ting Zhang +3

ICML 2026poster

Large Language Model (LLM) based code generation is predominantly formulated as a strictly monotonic process, appending tokens linearly to an immutable prefix. This formulation contrasts to the cognitive process of programming, which is inherently interleaved with forward generation and on-the-fly r…

Cited by 0 Source ↗Scholar ↗

2023

Fraud’s Bargain Attacks to Textual Classifiers via Metropolis-Hasting Sampling (Student Abstract)

Mingze Ni, Zhensu Sun, Wei Liu

AAAI 2023technical

Recent studies on adversarial examples expose vulnerabilities of natural language processing (NLP) models. Existing techniques for generating adversarial examples are typically driven by deterministic heuristic rules that are agnostic to the optimal adversarial examples, a strategy that often result…

Cited by 2 Source ↗PDF ↗Scholar ↗