Quiet Triggers, Loud Footprints: A Tri-Space Measurement Study of Backdoor Stealthiness
Backdoor attacks on deep neural networks are commonly evaluated by attack success rate and benign accuracy, yet their st
#cs.AI
共收录 1652 条相关情报。
← 返回所有主题Lost in the Fallback: How Reliably Do Typed Decision Models Use Fallback Options?
Typed decision models (TDMs) are increasingly used in applications such as request routing and model selection, making r
AWARE-RG: Abstraction Aware Explanation of Resiliency Graphs for Cyber Physical Systems
Understanding the security posture of cyber physical systems (CPS) requires reasoning across both information technology
Beyond Maliciousness: Static and Runtime Attack-Surface Profiling of Agent Skills
Agent skills are Markdown documents that a tool-using agent reads as instructions and then acts on with the privileges o
AgentCIScope: Grounded Contextual Integrity Evaluation for LLM Agents
LLM agents are becoming increasingly capable of handling daily workspace tasks by interacting with application environme
CyberArena: Benchmarking AI Agents in Live Symmetric Attack-and-Defense Combat
AI agents are demonstrating increasingly strong offensive and defensive cybersecurity capabilities in the real world. Cu
Bytes to Threats: Byte-Sequence Transformer For Malware Detection
Existing malware detection approaches heavily rely on handcrafted features derived from static or dynamic analysis of th
Nudge the Judge: Uncovering Program Decision Hijacking in Real-World Jev Applications
System One models such as Jev change how software makes decisions by mapping open-ended semantic contexts into structure
DPOison-VL: Clean Preference Poisoning in Vision-Language Direct Preference Optimization
Direct Preference Optimization (DPO) has become a widely adopted approach for aligning vision-language models (VLMs), ye
Rethinking Quality in Large Language Model Routing: Security-Conditioned Model-and-Budget Selection
Large language model (LLM) routers reduce serving cost by choosing which model to call and how many output tokens to gra
FedGraph: Defending Federated Large Language Model Fine-Tuning Against Backdoor Attacks via Graph-Based Aggregation
Federated fine-tuning of large language models (LLMs) allows multiple clients to collaboratively adapt models without sh
Encrypted Skills Can Become New Security Exploits If AI Agents Know How to Decipher
Third-party skills can expose LLM agents to malicious instructions hidden by encoding. We introduce Ciphered Skill Injec
Holding Agents Accountable with Verifiable Agent Insurance
While AI agents are useful for many tasks, they regularly misbehave in destructive ways, such as deleting important data
CompanionSafe: From Multi-turn Safety Evaluation to Guardrails for AI Companions
AI companions provide users with emotional support and ongoing companionship, but their sustained relational interaction
Cost-Efficient Privacy Enforcement for Email-Generating LLM Agents under Strategic Information Requests
LLM agents now act as delegated communication intermediaries: they read private context, draft messages, and send extern
ProtoArena: Can AI Agents Discover and Exploit Real-World Cross-Component Protocol Vulnerabilities?
Large language model (LLM) agents are increasingly used for vulnerability analysis, yet existing benchmarks provide limi
Same Attack, Different Judge: A First Controlled Adversarial Comparison of Jev, LLM Judges, and Purpose-Built Safety Classifiers
TypeSafe AI's Jev is a new kind of safety judge. It generates no text and no label: it answers questions the developer d
SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models
Agent skills turn natural-language instructions into actions, creating a security challenge: legitimate automation and m
Enhanced Detective: A Dual-Stage Proactive Defense Against Internal Poisoning Attacks in Financial Fraud Detection Using Federated Learning
With recent developments in Artificial Intelligence (AI), the adoption of distributed learning paradigms such as Federat
Mitigating Black-Box Score-Based Query Attacks via Gradient Confusion
Score-based black-box adversarial attacks pose a serious threat to deployed machine learning systems by exploiting repea