Inference-time safety methods for large language models have proliferated, yet no systematic comparison exists. We evaluate five defense paradigms (no defense, static steering, CAST, AlphaSteer, probe-gated) across seven instruction-tuned models (7-31B) and five attack types (GCG, AutoDAN, DeepInception, prefilling, intent laundering).
arXiv:2606. 29441v1 Announce Type: cross Abstract: Inference-time safety methods for large language models have proliferated, yet no systematic comparison exists.
arXiv:2606. 22686v2 Announce Type: replace-cross Abstract: Modern Large Language Models (LLMs) rely on extensive safety alignment, yet the mechanistic basis of refusal remains opaque.
A self-check defense asks the target model to assess a request before answering it; SAGE, the strongest published instance, reports an average 99% defense success rate. We show it can be breached by composing two attacks that are individually harmless against it: an established code-completion encoding and an established best-of-N search, neither of which exceeds 4.
arXiv:2606. 02822v1 Announce Type: cross Abstract: Production LLM applications stack several defense families -- refusal-phrase filters, token-budget controls, model allowlists, rate limits, tool-registry authentication -- yet existing breach-and-attack-simulation (BAS) benchmarks report a single aggregate coverage number, hiding which family closes which threat.
arXiv:2606. 27567v1 Announce Type: cross Abstract: Prompt injection is the top security risk for LLM-integrated applications, yet every defense proposed so far has been broken.
arXiv:2607. 26849v1 Announce Type: cross Abstract: As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time.
arXiv:2606. 05958v1 Announce Type: new Abstract: Activation steering has become a popular way to control Large Language Model (LLM) behavior without fine-tuning.
arXiv:2608. 05045v1 Announce Type: cross Abstract: Released aligned large language models remain vulnerable to malicious downstream finetuning.
arXiv:2607. 26639v1 Announce Type: cross Abstract: A self-check defense asks the target model to assess a request before answering it; SAGE, the strongest published instance, reports an average 99% defense success rate.
arXiv:2605. 08442v3 Announce Type: replace-cross Abstract: Persistent memory attacks against LLM agents achieve high attack success rates against open-source models.
arXiv:2608. 02657v1 Announce Type: cross Abstract: Agentic LLMs are vulnerable to indirect prompt injection (IPI) attacks, e.
arXiv:2607. 01859v1 Announce Type: new Abstract: Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching.