跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1284新增论文
+1011其中 AI 相关
+150已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 08:48 · 全站最近入库:2026-11-20 10:50各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 11:53 — 2026-11-20 11:53(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-20 08:48最近发现新增版本:2026-11-20 10:50库内论文最新更新时间:2026-11-19 12:39

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

28,155 已收录论文23,386 AI 相关8,624 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 2 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 08:46(北京时间)
新论文 · v1arXiv:2611.14970

Poison-then-Hide: Finetuning-Activated Backdoor Attack on Pretrained Vision Encoders

Qixuan Jin, Abinitha Gourabathina, Vinith Menon Suriyakumar, Walter Gerych, Marzyeh Ghassemi

原文摘要

Backdoor attacks threaten the integrity of machine learning models by allowing attackers to control model behavior through triggers. Models can be compromised during finetuning by backdoor attacks through either poisoned data or adversarial training objectives. Because existing finetuning-activated attacks assume limited domain shift or frozen encoder layers, they often fail under full-model finetuning. We target a stealthy finetuning-activated attack where a dormant backdoor is implanted in a pretrained encoder, and later activated by finetuning on clean downstream data. We propose Poison-then-Hide, a novel attack that remains effective when the entire model is finetuned in a domain transfer. Our approach consists of three components: trigger optimization, base encoder poisoning, and targeted unlearning to conceal the backdoor. We evaluate our method on six datasets and three model architectures, and achieve state-of-the-art (up to 97%) attack success rates. We find that jointly learning the benign target task alongside the poisoning is critical to the attack's success. We demonstrate standard detection and mitigation defenses cannot fully remove the backdoor, which can reappear after benign finetuning.

cs.LG · cs.CR · cs.CV

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.608ACL Anthology · ACL 2026

Answering the Wrong Question: Reasoning Trace Inversion for Abstention in LLMs

Abinitha Gourabathina Massachusetts Institute of Technology, Inkit Padhi, Manish Nagireddy IBM Research, Subhajit Chaudhury International Business Machines, Prasanna Sattigeri IBM Research

原文摘要

For Large Language Models (LLMs) to be reliably deployed, models must effectively know when not to answer: abstain. Reasoning models, in particular, have gained attention for impressive performance on complex tasks. However, reasoning models have been shown to have worse abstention abilities. Taking the vulnerabilities of reasoning models into account, we propose our Query Misalignment Framework. Hallucinations resulting in failed abstention can be reinterpreted as LLMs answering the wrong question (rather than answering a question incorrectly). Based on this framework, we develop a new class of state-of-the-art abstention methods called Trace Inversion. First, we generate the reasoning trace of a model. Based on only the trace, we then reconstruct the most likely query that the model responded to. Finally, we compare the initial query with the reconstructed query. Low similarity score between the initial query and reconstructed query suggests that the model likely answered the question incorrectly and is flagged to abstain. Extensive experiments demonstrate that Trace Inversion effectively boosts abstention performance in four frontier LLMs across nine abstention QA datasets, beating competitive baselines in 33 out of 36 settings. The code is available at this https://anonymous.4open.science/r/trace-inversion-08BB/.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表