Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2607.09804

Trivial Prompt Reframing Bypasses Safety Guardrails in Google\'s MedGemma-4B

Avi-ad Avraam Buskila
View original source ↗Read source document ↗Export metadata ↓

Abstract

Open-weight medical language models are increasingly used as the base of patient-facing and clinician-support applications. Their model cards prohibit specific behaviors -- recommending exact drug dosages, issuing definitive diagnoses, prescribing treatments, adjudicating drug-drug interactions, and advising that emergency care can be skipped -- yet a model card describes intended behavior, not robust behavior. We quantify that gap for MedGemma-4B-it under attacks that require no technical sophistication. We build a fully factorial benchmark of 5 guarded-behavior concepts x 50 deterministically templated questions x 6 lay-accessible attack manners x 3 repetitions (4,500 generations), serve the model locally through Ollama under default sampling, and code every response refuse/hedge/comply with three independent judges (an LLM judge, a transparent regex judge, and an NLI-entailment judge). Under the primary LLM judge the overall Attack Success Rate (ASR, the fraction coded comply) is 38.0%. The two framings that reinterpret the request as legitimate dominate: recasting a question as a "medical board exam" item raises ASR from a 29.0% baseline to 53.1% (+24.0 points), and an appeal to an alleged doctor's authority raises it to 43.7% (+14.7); crude instruction-override prefixes have no significant effect. Robustness is dominated by topic: the drug-interaction guardrail is nearly absent (83.2% ASR) while the emergency-deferral guardrail is strong (4.7%) -- and the authority framing is the only attack that breaches it. We report Wilson confidence intervals, cluster-bootstrap effect sizes, a cluster-robust logistic regression, Cochran's Q, per-manner McNemar tests, and inter-judge reliability (Fleiss' kappa = 0.26); absolute ASR is judge-dependent while the ordering of attacks and topics is not. Our findings motivate stronger deployment-time guardrails for open medical models.

Explore related subjects

cs.CRcs.AI

Keep this discovery

BibTeXRIS

Avi-ad Avraam Buskila. 2026-07-09. Trivial Prompt Reframing Bypasses Safety Guardrails in Google\'s MedGemma-4B. https://arxiv.org/abs/2607.09804

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Empirical Evaluation of Membership Inference Attacks on NLP Text Classifiers: A Baseline Study on SST-2

Membership inference attacks (MIAs) try to determine whether a specific record was used to train a model, a privacy risk that matters in natural language processing (NLP), where training data can contain sensitive user text. This paper presents a controlled benchmark of membership inference vulnerability for text classification on the GLUE SST-2 sentiment dataset. A TF-IDF + Logistic Regression pipeline and a fine-tuned DistilBERT classifier are compared under a loss-threshold MIA, with utility measured by development accuracy and macro F1. DistilBERT reached 0.9466 accuracy and 0.9460 macro F1 against 0.8756 and 0.8727 for Logistic Regression, yet both models leaked membership signal (Attack AUC 0.5615 and 0.5800, respectively). Two mitigations were tested. Stronger regularization reduced leakage for Logistic Regression at a visible utility cost, whereas fine-tuning DistilBERT for 2 epochs instead of 3 reduced leakage with negligible accuracy loss. Lightweight training adjustments can improve the privacy-utility trade-off without complex defenses.

cs.CR↗
arXiv2026

Empirical Evaluation of Data Poisoning Attacks in Supervised Learning

Data poisoning corrupts training data to degrade a model or to plant attacker-controlled behavior. This study evaluates two representative training-time attacks, label flipping and backdoor poisoning, on MNIST and Fashion-MNIST with three baseline classifiers: Logistic Regression, Linear SVM, and Random Forest. Clean training is compared with poisoning rates of 5%, 10%, and 20% using clean-test accuracy, macro-precision, macro-recall, macro-F1, and, for backdoors, attack success rate. Label flipping caused clear degradation, largest for Logistic Regression and Linear SVM, while Random Forest stayed comparatively stable. Backdoor poisoning reached attack success rates from 0.9667 to 1.0000 on both datasets and all three models while often keeping clean-test performance near baseline. The results separate indiscriminate poisoning, which shows up in standard metrics, from targeted backdoor poisoning, which stays comparatively stealthy while embedding highly effective malicious behavior, and they support security-oriented evaluation beyond conventional clean-test metrics.

cs.CR↗
arXiv2026

DeFiFusion: Combining Transaction Events with Smart Contracts to Detect Price Manipulation Attacks

Decentralized Finance (DeFi) has emerged as a rapidly growing blockchain-based financial service, where market transaction dynamics and underlying smart contract logic are intricately intertwined. This autonomous interplay, while eliminating centralized intermediaries, significantly expands the vulnerability surface of DeFi protocols to Price Manipulation Attacks (PMAs), which have already inflicted catastrophic financial losses. Despite their gravity, existing detection paradigms suffer from fundamental limitations. Transaction-centric methods lack awareness of contract execution semantics, making them prone to false positives under legitimate market volatility, while static contract analyses ignore real transaction behaviors and frequently report vulnerabilities that are infeasible to exploit in practice. We present DeFiFusion, a dual-modal PMA detection framework that closes this gap by jointly modeling transaction events and smart contract semantics within a unified pipeline. Our core insight is that PMA maliciousness emerges only from the interaction between transaction behaviors and the contract logic they exploit; neither signal suffices in isolation. Accordingly, we derive price-manipulation-aware event encoding for extracting fine-grained temporal and economic features tailored to manipulation patterns. We further introduce LLM-based contract semantic extraction to supply the execution-logic context that prior behavioral methods lack. To fuse these modalities, we propose a Dual-Modal Projection-Fusion Transformer with T5-style relative positional encoding, capturing the cyclic multi-stage execution structures that distinguish PMAs from benign market activity. Extensive experiments demonstrate that DeFiFusion consistently achieves state-of-the-art detection performance, effectively recalling 222 of the 225 PMA cases while maintaining a precision of 96.10%.

cs.CR↗