File size: 3,067 Bytes
1a4aa87
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
"""

AegisLM Benchmarking Module



Provides benchmarking capabilities for evaluating LLM robustness:

- Baseline evaluation mode

- Adversarial evaluation mode

- Delta robustness computation

- Cross-model comparison

- Statistical reporting

- Benchmark artifact generation

"""

from backend.benchmarking.comparison import (
    compare_models,
    find_most_robust_model,
    find_most_stable_model,
    find_most_vulnerable_model,
    generate_comparative_report,
    generate_vulnerability_heatmap,
    get_attack_type_vulnerability,
    rank_models,
)
from backend.benchmarking.engine import (
    BenchmarkEngine,
    BenchmarkEvent,
    get_benchmark_engine,
)
from backend.benchmarking.reporter import (
    DEFAULT_BENCHMARK_DIR,
    export_to_csv,
    generate_benchmark_artifact,
    generate_summary_report,
    generate_text_report,
    list_benchmarks,
    load_benchmark_artifact,
)
from backend.benchmarking.schemas import (
    BenchmarkMode,
    BenchmarkPerformance,
    BenchmarkResult,
    BenchmarkStatus,
    BenchmarkWeights,
    EvaluationResult,
    MetricDeltas,
    ModelBenchmarkResult,
    ModelMetrics,
    ModelRanking,
    StartBenchmarkRequest,
    StartBenchmarkResponse,
    VulnerabilityHeatmap,
    VulnerabilityHeatmapCell,
)
from backend.benchmarking.statistics import (
    MetricStatistics,
    calculate_confidence_interval,
    calculate_mean,
    calculate_mean_with_ci,
    calculate_paired_differences,
    calculate_standard_deviation,
    calculate_variance,
    calculate_sample_std,
    cohens_d,
    calculate_vulnerability_consistency,
    generate_summary_statistics,
    paired_t_test,
)


__all__ = [
    # Comparison
    "compare_models",
    "find_most_robust_model",
    "find_most_stable_model",
    "find_most_vulnerable_model",
    "generate_comparative_report",
    "generate_vulnerability_heatmap",
    "get_attack_type_vulnerability",
    "rank_models",
    # Engine
    "BenchmarkEngine",
    "BenchmarkEvent",
    "get_benchmark_engine",
    # Reporter
    "DEFAULT_BENCHMARK_DIR",
    "export_to_csv",
    "generate_benchmark_artifact",
    "generate_summary_report",
    "generate_text_report",
    "list_benchmarks",
    "load_benchmark_artifact",
    # Schemas
    "BenchmarkMode",
    "BenchmarkPerformance",
    "BenchmarkResult",
    "BenchmarkStatus",
    "BenchmarkWeights",
    "EvaluationResult",
    "MetricDeltas",
    "ModelBenchmarkResult",
    "ModelMetrics",
    "ModelRanking",
    "StartBenchmarkRequest",
    "StartBenchmarkResponse",
    "VulnerabilityHeatmap",
    "VulnerabilityHeatmapCell",
    # Statistics
    "MetricStatistics",
    "calculate_confidence_interval",
    "calculate_mean",
    "calculate_mean_with_ci",
    "calculate_paired_differences",
    "calculate_standard_deviation",
    "calculate_variance",
    "calculate_sample_std",
    "cohens_d",
    "calculate_vulnerability_consistency",
    "generate_summary_statistics",
    "paired_t_test",
]